DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement(s)
The Information disclosure statement (IDS) filed on January 27th, 2025 has been acknowledged and considered by the examiner.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitation(s) that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that use the word “means” or “step” but are nonetheless not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph because the claim limitation(s) recite(s) sufficient structure, materials, or acts to entirely perform the recited function.
Claims 1, 14 and 19, recite(s) limitation(s) that use words like “means” (or “step”) or similar terms with functional language and do invoke 35 U.S.C. 112(f):
Claim 1; recites the limitation, “generating,…using an object detection model, an object matrix….” [Line 5].
Claims 14; recites the limitation, “generate, using an object detection model, an object matrix…” [Line 5].
Claims 19; recites the limitation, “generate, using an object detection model, an object matrix…” [Line 5].
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
After a careful analysis, as disclosed above, and a careful review of the specification the following limitations in claims 1, 14 and 19;
(i) “an object detection model” as supported in Paragraphs [0064-0065] of the instant specification, filed on October 15th, 2024, which discloses “the object detection model may include a machine learning model including one or more supervised, unsupervised, semi-supervised, reinforcement learning models, and/or the like. In some examples, the object detection model may include multiple models configured to perform one or more different stages of a corner detection process…The object detection model may be trained using one or more supervised machine learning techniques, such as back propagation of errors (e.g., a weighted-fusion layer error propagation, side-output layer error propagation, etc.)” thus have sufficient structure or material/act wherein is a machine learning model including one or more supervised, unsupervised, semi-supervised, reinforcement learning models.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 12-16 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) and Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”).
(as best understood based on the 112f interpretation above) Regarding claim 1, Smith explicitly teaches a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors (Col. 2, lines 1-4, discloses “performed by a computer system comprising a processor; and enumerating, by the processor…”), an object-specific denoised image frame for an image frame (Col 24., lines 28-38, discloses “the visual images were first denoised using a total-variance constrained denoising technique…for identifying small and dim platelets” therefore, the denoised image is analogous to object-specific denoised image frame as claimed) based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]); generating, by the one or more processors, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”); generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results); tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result (Col. 6, lines 7-27, discloses “the invention can…cells can be tracked” indicating tracking of the target object as the result of the processing as discussed including using the information of the target object candidates [template images]); and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records” therefore, the recorded subject is analogous to the recited “target object” as claimed, which is the result of the process of the invention, as discussed, including the result of the tracking of the tracked target object based on the object-specific result); and modifying, by the one or more processors, an object-specific count for the recorded target object (Col. 13, lines 20-35, discloses “provide an overview of a subject’s general health status….acquiring a complete blood cell count…to obtain accurate counts” indicating obtaining a blood count for the subject’s general health [analogous to an object-specific count for the recorded target object]; moreover, Col 16, lines 50-67, discloses “once identified, a cell can be counted…once the number of….cells or platelets is counted, subpopulations and related percentages can be determined” indicating modifying a number of count when a cell or platelet is identified).
However, Smith does not explicitly teach generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates; the object-specific result being object-specific attributes.
In the same field of object tracking using cross-correlation (Title and Abstract, Habibian), Habibian explicitly teaches teach generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates (Col. 12, lines 64-67, and Col. 13, lines 1-23, discloses “the cross-correlation layer convolves the extracted target region representation with the extracted search region representation to determine a cross-correlation map. The cross-correlation map is used to predict the location of a target…to predict the location of the target in the second frame” indicating using a neural network layer [the cross-correlation layer which is analogous to the recited “object detection model”] to obtain a cross-correlation map [analogous to Smith’s cross-correlation map which was mapped to the recited “object matrix”] wherein, the cross-correlation is used to make predictions of the target locations which is analogous to the recited “one or more target object candidates”; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates, wherein the cross-correlation map as a matrix can be obtained using a layer of a neural network. Thus in order to have such method to improve training of a neural network for object tracking using such object detection method of such neural network approach, see Habibian’s Col. 1, lines 26-35 and Col. 2, lines 1-5).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame. Moreover, Smith’s generating of an object matrix can be modified to be based on the use of an object detection model as taught in Habibian.
Such a modification is the result of combing prior art elements. Smith and Habibian share the same field of endeavor of object detection based on cross-correlation. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame. The motivation for the proposed modification would have been to have such approach, thus to improve training of a neural network for object tracking using such object detection method of such neural network approach, see Habibian’s Col. 1, lines 26-35 and Col. 2, lines 1-5.
However, Smith in view of Habibian does not explicitly teach the object-specific result being object-specific attributes.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
Regarding claim 2, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computer-implemented method of claim 1, wherein Smith explicitly teaches further comprising: modifying a total object count in response to the object-specific count satisfying a threshold detection count (Col. 24, lines 40-50, discloses “for each platelet image the count was performed at a wide range of thresholds” indicating the modifying of a total object count is based on satisfying a threshold detection count [range of thresholds]).
Regarding claim 3, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computer-implemented method of claim 1, wherein Smith explicitly teaches wherein the object matrix is indicative of a plurality of points of interest for each of the one or more target object candidates (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”, moreover, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”) and the plurality of object-specific result is based on the plurality of points of interest (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results, and the cross-correlation is indicative of the points of interests as discussed, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”).
However, Smith in view of Habibian, in combination, does not explicitly teach the object-specific result being object-specific attributes.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
Regarding claim 12, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computer-implemented method of claim 1, wherein Smith explicitly teaches wherein the one or more shared object attributes are indicative of an object consistency, an object color, and an object opacity (“one or more” indicates a selection, therefore, only one of the options is the instant scope of the claim, the examiner selects “an object color” to be mapped which is taught in Smith’s Col. 24, lines 20-50, which discloses “the size of each particle was analyzed in the count mask, and objects with very large sizes were discarded filter out white cells (which also fluoresce red) from the platelet count. Because different subjects have different amounts of platelet fluorescence” indicating different fluorescence colors [different amounts of platelet fluorescence such as fluorescing red]).
Regarding claim 13, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computer-implemented method of claim 1, wherein Smith explicitly teaches further comprising: adjusting the contrast threshold based on a modification to the one or more shared object attributes (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”], moreover, the image was binarized by setting a specific threshold value indicating adjusting of the contrast threshold as claimed, size and variance attribute are analogous to the disclosed shared object attributes, therefore, specifying the specific threshold is analogous to “a modification to one or more shared-object attributes” as claimed, since specifying a variance threshold is a modification to an information regarding a shared attribute between objects, being a modification to a threshold which is used to identify objects according to their variances).
(as best understood based on the 112f interpretation above) Regarding claim 14, Smith explicitly teaches a computing system comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to (Col. 2, lines 1-4, discloses “performed by a computer system comprising a processor; and enumerating, by the processor…”): generate an object-specific denoised image frame for an image frame (Col 24., lines 28-38, discloses “the visual images were first denoised using a total-variance constrained denoising technique…for identifying small and dim platelets” therefore, the denoised image is analogous to object-specific denoised image frame as claimed) based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]); generate an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”); generate, a plurality of object-specific result for the one or more target object candidates based on the object matrix (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results); track the tracked target object from the one or more target object candidates based on the plurality of object-specific result (Col. 6, lines 7-27, discloses “the invention can…cells can be tracked” indicating tracking of the target object as the result of the processing as discussed including using the information of the target object candidates [template images]); and in response to tracking the tracked target object, record a recorded target object corresponding to the tracked target object based on the plurality of object-specific result (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records” therefore, the recorded subject is analogous to the recited “target object” as claimed, which is the result of the process of the invention, as discussed, including the result of the tracking of the tracked target object based on the object-specific result); and modify an object-specific count for the recorded target object (Col. 13, lines 20-35, discloses “provide an overview of a subject’s general health status….acquiring a complete blood cell count…to obtain accurate counts” indicating obtaining a blood count for the subject’s general health [analogous to an object-specific count for the recorded target object]; moreover, Col 16, lines 50-67, discloses “once identified, a cell can be counted…once the number of….cells or platelets is counted, subpopulations and related percentages can be determined” indicating modifying a number of count when a cell or platelet is identified).
However, Smith does not explicitly teach generate, using an object detection model, an object matrix indicative of one or more target object candidates; the object-specific result being object-specific attributes.
In the same field of object tracking using cross-correlation (Title and Abstract, Habibian), Habibian explicitly teaches teach generate, using an object detection model, an object matrix indicative of one or more target object candidates (Col. 12, lines 64-67, and Col. 13, lines 1-23, discloses “the cross-correlation layer convolves the extracted target region representation with the extracted search region representation to determine a cross-correlation map. The cross-correlation map is used to predict the location of a target…to predict the location of the target in the second frame” indicating using a neural network layer [the cross-correlation layer which is analogous to the recited “object detection model”] to obtain a cross-correlation map [analogous to Smith’s cross-correlation map which was mapped to the recited “object matrix”] wherein, the cross-correlation is used to make predictions of the target locations which is analogous to the recited “one or more target object candidates”; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates, wherein the cross-correlation map as a matrix can be obtained using a layer of a neural network. Thus in order to have such method to improve training of a neural network for object tracking using such object detection method of such neural network approach, see Habibian’s Col. 1, lines 26-35 and Col. 2, lines 1-5).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame. Moreover, Smith’s generating of an object matrix can be modified to be based on the use of an object detection model as taught in Habibian.
Such a modification is the result of combing prior art elements. Smith and Habibian share the same field of endeavor of object detection based on cross-correlation. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame. The motivation for the proposed modification would have been to have such approach, thus to improve training of a neural network for object tracking using such object detection method of such neural network approach, see Habibian’s Col. 1, lines 26-35 and Col. 2, lines 1-5.
However, Smith in view of Habibian does not explicitly teach the object-specific result being object-specific attributes.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
Regarding claim 15, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computing system of claim 14, wherein Smith explicitly teaches wherein the one or more processors are further configured to: modify a total object count in response to the object-specific count satisfying a threshold detection count (Col. 24, lines 40-50, discloses “for each platelet image the count was performed at a wide range of thresholds” indicating the modifying of a total object count is based on satisfying a threshold detection count [range of thresholds]).
Regarding claim 16, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computing system of claim 14, wherein Smith explicitly teaches wherein the object matrix is indicative of a plurality of points of interest for each of the one or more target object candidates (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”, moreover, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”) and the plurality of object-specific result is based on the plurality of points of interest (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results, and the cross-correlation is indicative of the points of interests as discussed, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”).
However, Smith in view of Habibian, in combination, does not explicitly teach the object-specific result being object-specific attributes.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
(as best understood based on the 112f interpretation above) Regarding claim 19, Smith explicitly teaches one or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to (Col. 2, lines 1-4, discloses “performed by a computer system comprising a processor; and enumerating, by the processor…” indicating the use of a computer which can be understood to have a component of a non-transitory computer-readable storage media such as a RAM or ROM): generate an object-specific denoised image frame for an image frame (Col 24., lines 28-38, discloses “the visual images were first denoised using a total-variance constrained denoising technique…for identifying small and dim platelets” therefore, the denoised image is analogous to object-specific denoised image frame as claimed) based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]); generate an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”); generate, a plurality of object-specific result for the one or more target object candidates based on the object matrix (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results); track the tracked target object from the one or more target object candidates based on the plurality of object-specific result (Col. 6, lines 7-27, discloses “the invention can…cells can be tracked” indicating tracking of the target object as the result of the processing as discussed including using the information of the target object candidates [template images]); and in response to tracking the tracked target object, record a recorded target object corresponding to the tracked target object based on the plurality of object-specific result (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records” therefore, the recorded subject is analogous to the recited “target object” as claimed, which is the result of the process of the invention, as discussed, including the result of the tracking of the tracked target object based on the object-specific result); and modify an object-specific count for the recorded target object (Col. 13, lines 20-35, discloses “provide an overview of a subject’s general health status….acquiring a complete blood cell count…to obtain accurate counts” indicating obtaining a blood count for the subject’s general health [analogous to an object-specific count for the recorded target object]; moreover, Col 16, lines 50-67, discloses “once identified, a cell can be counted…once the number of….cells or platelets is counted, subpopulations and related percentages can be determined” indicating modifying a number of count when a cell or platelet is identified).
However, Smith does not explicitly teach generate, using an object detection model, an object matrix indicative of one or more target object candidates; the object-specific result being object-specific attributes.
In the same field of object tracking using cross-correlation (Title and Abstract, Habibian), Habibian explicitly teaches teach generate, using an object detection model, an object matrix indicative of one or more target object candidates (Col. 12, lines 64-67, and Col. 13, lines 1-23, discloses “the cross-correlation layer convolves the extracted target region representation with the extracted search region representation to determine a cross-correlation map. The cross-correlation map is used to predict the location of a target…to predict the location of the target in the second frame” indicating using a neural network layer [the cross-correlation layer which is analogous to the recited “object detection model”] to obtain a cross-correlation map [analogous to Smith’s cross-correlation map which was mapped to the recited “object matrix”] wherein, the cross-correlation is used to make predictions of the target locations which is analogous to the recited “one or more target object candidates”; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates, wherein the cross-correlation map as a matrix can be obtained using a layer of a neural network. Thus in order to have such method to improve training of a neural network for object tracking using such object detection method of such neural network approach, see Habibian’s Col. 1, lines 26-35 and Col. 2, lines 1-5).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame. Moreover, Smith’s generating of an object matrix can be modified to be based on the use of an object detection model as taught in Habibian.
Such a modification is the result of combing prior art elements. Smith and Habibian share the same field of endeavor of object detection based on cross-correlation. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame. The motivation for the proposed modification would have been to have such approach, thus to improve training of a neural network for object tracking using such object detection method of such neural network approach, see Habibian’s Col. 1, lines 26-35 and Col. 2, lines 1-5.
However, Smith in view of Habibian does not explicitly teach the object-specific result being object-specific attributes.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
Claims 4 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) further in view of Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”) and Hamid K. Aghajan et. al. (“US 5,311,600” hereinafter as “Aghajan”).
Regarding claim 4, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computer-implemented method of claim 3, wherein Smith explicitly teaches the plurality of points of interest for the tracked target object (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”, moreover, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”).
However, Smith in view of Habibian and Kincaid, in combination, does not explicitly teach the object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points.
In the same field of object detection based on sharp peaks (Abstract and Col. 6, lines 1-17, Aghajan), Aghajan explicitly teach the object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points (Col. 1, lines 31-55, discloses “edges can be represented by sharp discontinuities…where the edge profiles are smoothed out and blurred and the corners are rounded” indicating the edge profiles can represent and resulted in corners, therefore the two terms can be understood to be correlated, Col. 6, lines 1-17, discloses “where sharp negative peakings represent the edge locations” wherein sharp peakings here are analogous to the sharp pears of Smith, representing the locations of the target detection objects, hence, they are analogous which is mapped to the plurality of points of interests, here Aghajan further teaches that these sharp peaks and object locations are based on a plurality of corner points as well, being the “edge profiles…and the corners”; moreover, Col. 5, lines 43-49, discloses “the neural network classification technique is applied to edge detection” indicating using a neural network model for the edge/corner detection [therefore, is analogous to the recited “corner detection”] therefore, the object detection can include corner detection of Aghajan; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect sharp peaks for locations of objects in an image, wherein the sharp peaks can represent corner locations to be part of a corner detection model to be used with an object detection model neural network. Thus in order to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy, see Aghajan’s Abstract.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and Smith’s generating of an object matrix can be modified to be further based on using an object detection model as taught by Habibian. Moreover, Habibian’s object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points for the tracked target object as taught in Aghajan.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid and Aghajan share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; wherein the object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points for the tracked target object. Thus to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy, see Aghajan’s Abstract.
Regarding claim 17, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computing system of claim 16, wherein Smith explicitly teaches the plurality of points of interest for the tracked target object (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”, moreover, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”).
However, Smith in view of Habibian and Kincaid, in combination, does not explicitly teach the object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points.
In the same field of object detection based on sharp peaks (Abstract and Col. 6, lines 1-17, Aghajan), Aghajan explicitly teach the object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points (Col. 1, lines 31-55, discloses “edges can be represented by sharp discontinuities…where the edge profiles are smoothed out and blurred and the corners are rounded” indicating the edge profiles can represent and resulted in corners, therefore the two terms can be understood to be correlated, Col. 6, lines 1-17, discloses “where sharp negative peakings represent the edge locations” wherein sharp peakings here are analogous to the sharp pears of Smith, representing the locations of the target detection objects, hence, they are analogous which is mapped to the plurality of points of interests, here Aghajan further teaches that these sharp peaks and object locations are based on a plurality of corner points as well, being the “edge profiles…and the corners”; moreover, Col. 5, lines 43-49, discloses “the neural network classification technique is applied to edge detection” indicating using a neural network model for the edge/corner detection [therefore, is analogous to the recited “corner detection”] therefore, the object detection can include corner detection of Aghajan; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect sharp peaks for locations of objects in an image, wherein the sharp peaks can represent corner locations to be part of a corner detection model to be used with an object detection model neural network. Thus in order to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy, see Aghajan’s Abstract.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and Smith’s generating of an object matrix can be modified to be further based on using an object detection model as taught by Habibian. Moreover, Habibian’s object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points for the tracked target object as taught in Aghajan.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid and Aghajan share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; wherein the object detection model comprises a corner detection model and the plurality of points of interest are based on a plurality of corner points for the tracked target object. Thus to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy, see Aghajan’s Abstract.
Claims 5-6 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) further in view of Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”) and Hamid K. Aghajan et. al. (“US 5,311,600” hereinafter as “Aghajan”) and Tong Zhang (“US 6,985,631 B2” hereinafter as “Zhang”).
Regarding claim 5, Smith in view of Habibian and Kincaid and Aghajan, in combination, explicitly teaches the computer-implemented method of claim 4, wherein Smith explicitly teaches the plurality of object-specific result (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results) is indicative of (i) a number of the plurality of points of interest for the tracked target object (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”, moreover, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”; wherein, differentiating cells indicating object-specific results, and the cross-correlation is indicative of the points of interests as discussed) and (ii) an object size of the tracked target object based on the plurality of points of interest (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”]; indicating the size of the target object is based on the sharp edges as well [points of interest]), and wherein the computer-implemented method further comprises: identifying the tracked target object based on (i) a first comparison between the object size and a target object size threshold (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, indicating that the size of the target object is being compared to a size threshold to filter out large size objects).
However, Smith in view of Habibian and Aghajan, in combination, does not explicitly teach the object-specific result being object-specific attributes; identifying the tracked target object based on (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
However, Smith in view of Habibian and Aghajan and Kincaid, in combination, does not explicitly teach identifying the tracked target object based on (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold.
In the same field of edge detection (Title and Abstract, Zhang), Zhang explicitly teaches identifying the tracked target object based on (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold (Col. 7, lines 3-21, discloses “top edge that corresponds to frame. Top edge comprises two portions that are associated with two different real edges…sign of the slope, the turning point N may be detected. Additionally, the sharpness at the turning point….the sharpness threshold is utilized to cause the analysis to be robust against noise” therefore, the number such as number of edges, sign of the slope, turning point N are number of the plurality of points [of the edges detected] including the slope or sharpness to be compared to a sharpness threshold [target object corner threshold as claimed] to detect a corner, Col. 10, lines 32-34, discloses “the corner locations may be estimated”; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect sharp peaks for locations of objects in an image, wherein the sharp peaks can represent corner locations to be part of a corner detection model to be used with an object detection model neural network, these sharp peaks/edges being a plurality of points used to track an objects, wherein these points can be based on a number of the plurality of points being compared to a threshold to represent a corner detected. Thus in order to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy so that the image correction can be perform effectively, see Zhang’s Col. 3, lines 36-46).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, wherein a plurality of object-specific result is indicative of (i) a number of the plurality of points of interest for the tracked target object and (ii) an object size of the tracked target object based on the plurality of points of interest, and wherein the computer-implemented method further comprises: identifying the tracked target object based on (i) a first comparison between the object size and a target object size threshold. Moreover, Habibian’s object-specific result being object-specific attribute as taught by Kincaid, and Smith’s identifying the tracked target object can further modified to be based on a second comparison between the number of the plurality of points of interest and a target object corner threshold as taught in Zhang.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid and Aghajan and Zhang share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, wherein a plurality of object-specific attributes is indicative of (i) a number of the plurality of points of interest for the tracked target object and (ii) an object size of the tracked target object based on the plurality of points of interest, and wherein the computer-implemented method further comprises: identifying the tracked target object based on (i) a first comparison between the object size and a target object size threshold and (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold. Thus in order to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy so that the image correction can be perform effectively, see Zhang’s Col. 3, lines 36-46.
Regarding claim 6, Smith in view of Habibian further in view of Kincaid and Aghajan and Zhang, in combination, explicitly teaches the computer-implemented method of claim 5, wherein Smith explicitly teaches wherein the target object size threshold is based on the one or more shared object attributes (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]).
Regarding claim 18, Smith in view of Habibian and Kincaid and Aghajan, in combination, explicitly teaches computing system of claim 16, wherein Smith explicitly teaches the plurality of object-specific result (Col. 25, lines 4-25, discloses “for each template, a binary image was created wherein regions of extended maxima in the cross-correlation were defined as one and all other portions of the image were defined as zero. ..identify regions of the background that have larger correlation values than their neighbors” indicating using the cross correlation map to identify cells within each template image [analogous to the recited “for the one or more target object candidates based on the object matrix”]; moreover, Col. 25, lines 26-35, discloses “the images were submitted to automated routines to enumerate and differentiate cells” wherein, differentiating cells indicating object-specific results) is indicative of (i) a number of the plurality of points of interest for the tracked target object (Col. 24, lines 51-67, discloses “several template images were created, each template consisting of a single red blood cell on a background…when the cells in a template cells were similar to the cells in the visual image, the cross correlation between images consisted of several sharp peaks at the locations of cells within the image” indicating target object candidates [several template images] and indicating a matrix being indicative of the template images [analogous to the “cross correlation map” being a matrix], Col. 25, lines 1-4, discloses “to identify and count each cells, regions of the cross correlation map….”, moreover, the “several sharp peaks at the locations of cells within the image” is analogous to the recited “indicative of a plurality of points of interest for each of the one or more target object candidates”; wherein, differentiating cells indicating object-specific results, and the cross-correlation is indicative of the points of interests as discussed) and (ii) an object size of the tracked target object based on the plurality of points of interest (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”]; indicating the size of the target object is based on the sharp edges as well [points of interest]), and wherein the computer-implemented method further comprises: identifying the tracked target object based on (i) a first comparison between the object size and a target object size threshold (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, indicating that the size of the target object is being compared to a size threshold to filter out large size objects).
However, Smith in view of Habibian and Aghajan, in combination, does not explicitly teach the object-specific result being object-specific attributes; identifying the tracked target object based on (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold.
In the same field of image-based cell identification (Title and Abstract, Kincaid), Kincaid explicitly teaches the object-specific result being object-specific attributes (Par. [0085] discloses “differently colored boundary high light may be displayed around the respective4 cells…to indicate their classification” and, Par. [0086] discloses “staining representing classes of cells or sub-cellular components may replace or overlay…” indicating using staining method to identify cells based on their respective color attributes, moreover, Par. [0003] discloses “attributes processing has involved making an image of cells from which quantitative information characterizing the cells is then derived” therefore, the attributes that characterize the individual cells is analogous to object-specific attributes as claimed, being used to differentiate the cells [analogous to Smith’s differentiating of the cells]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of obtaining a cross-correlation map as a matrix to make predictions of template images of object candidates and differentiate cells according to their template images and the cross-correlation map as a matrix result, wherein the differentiating of cells can be based on attributes of each of the cells. Thus in order to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of an method of generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific result for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific result; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific result. Moreover, Smith’s object-specific result is based on object-specific attributes as taught in Kincaid.
Such a modification is the result of combing prior art elements. Smith and Kincaid share the same field of endeavor of cell identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame and generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. The motivation for the proposed modification would have been to have such approach, thus to have such method of to obtain cell characterization that can distinguish them in a quantitatively approach that is more effective in identify cells based on their characteristic, see Kincaid’s Par. [0003] and Par. [0006].
However, Smith in view of Habibian and Aghajan and Kincaid, in combination, does not explicitly teach identifying the tracked target object based on (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold.
In the same field of edge detection (Title and Abstract, Zhang), Zhang explicitly teaches identifying the tracked target object based on (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold (Col. 7, lines 3-21, discloses “top edge that corresponds to frame. Top edge comprises two portions that are associated with two different real edges…sign of the slope, the turning point N may be detected. Additionally, the sharpness at the turning point….the sharpness threshold is utilized to cause the analysis to be robust against noise” therefore, the number such as number of edges, sign of the slope, turning point N are number of the plurality of points [of the edges detected] including the slope or sharpness to be compared to a sharpness threshold [target object corner threshold as claimed] to detect a corner, Col. 10, lines 32-34, discloses “the corner locations may be estimated”; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect sharp peaks for locations of objects in an image, wherein the sharp peaks can represent corner locations to be part of a corner detection model to be used with an object detection model neural network, these sharp peaks/edges being a plurality of points used to track an objects, wherein these points can be based on a number of the plurality of points being compared to a threshold to represent a corner detected. Thus in order to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy so that the image correction can be perform effectively, see Zhang’s Col. 3, lines 36-46).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, wherein a plurality of object-specific result is indicative of (i) a number of the plurality of points of interest for the tracked target object and (ii) an object size of the tracked target object based on the plurality of points of interest, and wherein the computer-implemented method further comprises: identifying the tracked target object based on (i) a first comparison between the object size and a target object size threshold. Moreover, Habibian’s object-specific result being object-specific attribute as taught by Kincaid, and Smith’s identifying the tracked target object can further modified to be based on a second comparison between the number of the plurality of points of interest and a target object corner threshold as taught in Zhang.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid and Aghajan and Zhang share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, wherein a plurality of object-specific attributes is indicative of (i) a number of the plurality of points of interest for the tracked target object and (ii) an object size of the tracked target object based on the plurality of points of interest, and wherein the computer-implemented method further comprises: identifying the tracked target object based on (i) a first comparison between the object size and a target object size threshold and (ii) a second comparison between the number of the plurality of points of interest and a target object corner threshold. Thus in order to have such method of detecting edges/target objects using such edge detection approach in an effective approach with more accuracy so that the image correction can be perform effectively, see Zhang’s Col. 3, lines 36-46.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) further in view of Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”) and Hamid K. Aghajan et. al. (“US 5,311,600” hereinafter as “Aghajan”) and Tong Zhang (“US 6,985,631 B2” hereinafter as “Zhang”) and Michael Zahniser et. al. (“US 8,339,586 B2” hereinafter as “Zahniser”).
Regarding claim 7, Smith in view of Habibian further in view of Kincaid and Aghajan and Zhang, in combination, explicitly teaches the computer-implemented method of claim 6, wherein Smith explicitly teaches wherein the one or more shared object attributes are indicative of a size for a plurality of calibration target objects (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]) and the target object size threshold (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]).
However, Smith in view of Habibian further in view of Kincaid and Aghajan and Zhang, in combination, does not explicitly teach wherein the one or more shared object attributes are indicative of a minimum size for a plurality of calibration target objects; and the target object size threshold is a percentage of the minimum size.
In the same field of cell detection based on size (Title and Abstract, Zahniser), Zahniser explicitly teaches wherein the one or more shared object attributes are indicative of a minimum size for a plurality of calibration target objects (Col. 17, lines 50-64, discloses “the ratio of this cell perimeter value squared to the cell area value is determined to check….cells with a ratio of the perimeter squared to the area, which exceeds the minimum value of 4pi by a threshold amount or more, are excluded from further analysis. Typically, the threshold amount is a percentage of the minimum value of 4pi” indicating that the size threshold [cell perimeter value and cell area value being compared, taking a ratio of, being compared to a threshold amount] being indicative of a minimum value of the 4pi [is analogous to the recited minimum size] for the detections a circular outline, the detection of the cells is used for a calibration process, Col. 22, lines 57-67, discloses “a device can be used to analyze control compositions to assess the accuracy of the results produced by the device…the device can be re-calibrated. Re-calibration can include, for example, re-determining values for some or all the weight coefficients” indicating using the result of the device as discussed, being the determined cells detected, to be determine accuracy, therefore, these possible detections used for this re-calibration is analogous to the recited calibration target objects); and the target object size threshold is a percentage of the minimum size (Col. 17, lines 50-64, discloses “the ratio of this cell perimeter value squared to the cell area value is determined to check….cells with a ratio of the perimeter squared to the area, which exceeds the minimum value of 4pi by a threshold amount or more, are excluded from further analysis. Typically, the threshold amount is a percentage of the minimum value of 4pi” indicating the threshold is a percentage of the minimum size [the threshold amount is a percentage of the minimum value of 4pi]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect objects based on common size threshold, wherein the size threshold being a minimum size for a plurality of objects being detected, wherein the result is then being used to determine accuracy of the detection to perform a re-calibration process using the detected results, moreover, the threshold being a percentage of the minimum 4pi size. Thus in order to have such method of performing using objects results to be compared and determined accuracy to perform a calibration process to improve accuracy of the method, see Zahniser’s Col. 22, lines 57-67).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method with one or more shared object attributes. Moreover, Smith’s shared object attributes can be modified to be indicative of a minimum size for a plurality of calibration target objects and the target object size threshold is a percentage of the minimum size as taught in Zahniser.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid and Aghajan and Zhang and Zahniser share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method with one or more shared object attributes are indicative of a minimum size for a plurality of calibration target objects and the target object size threshold is a percentage of the minimum size. Thus in order to have such method of performing using objects results to be compared and determined accuracy to perform a calibration process to improve accuracy of the method, see Zahniser’s Col. 22, lines 57-67.
Claims 8-9 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) further in view of Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”) and Maria Bordukova et. al. (“US 2026/0148813 A1” hereinafter as “Bordukova”).
Regarding claim 8, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the computer-implemented method of claim 1, wherein Smith explicitly teaches wherein the recorded target object is stored within a temporary object lookup structure (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records” therefore, the recorded subject is analogous to the recited “target object” as claimed, which is the result of the process of the invention, as discussed, including the result of the tracking of the tracked target object based on the object-specific result, wherein the subject’s health records is analogous to the recited “temporary object lookup structure”) and comprises a plurality of recorded object attributes (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records”; wherein the information being recorded such as analysis of visual data including a cell type, or an analyte, present in a body fluid and more, these are analogous to the recited “recorded object attributes”) indicative of a recorded object size (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the analysis of the visual data also include information about sizes of the cell as well).
However, Smith in view of Habibian and Kincaid, in combination, does not explicitly teach a plurality of recorded object attributes indicative of a recorded object vertical position, and the object-specific count.
In the same field of predicting subject-related attributes (Title and Abstract, Bordukova), Bordukova explicitly teaches a plurality of recorded object attributes indicative of a recorded object vertical position (Par. [0020] discloses “longitudinal characteristics of actual patients. With the aid of digital twins, it becomes feasible to generate entire and realistic clinical patient trajectories” moreover, Par. [0031] discloses “the clinical input comprises a medical history of a subject, the medical history comprising a plurality of values of subject-related attributes…values for at least one longitudinal attributes” therefore, the subject’s medical history including trajectories is analogous to the recited recorded object as claimed, and the longitudinal attributes is being analogous to vertical position as claimed, moreover, Par. [0006] discloses “complex, multimodal, multidimensional and longitudinal data” indicating the data can be longitudinal and multidimensional [can cover dimension in the vertical information as well, moreover, vertical position in a context can be understood to be a longitudinal position as well]), and the object-specific count (Page 17 shows the list of subject-related attributes which includes blood cell count [analogous to object-specific count as claimed]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect objects to track the objects and record them based on recorded object attributes being indicative of attributes such as recorded object size, wherein the recorded object attributes include multidimensional and longitudinal attributes and blood cell count. Thus in order to use such method for predicting of subject-related attributes with high efficacy, see Bordukova’s Par. [0003]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the recorded target object is stored within a temporary object lookup structure and comprises a plurality of recorded object attributes indicative of a recorded object size. Moreover, Smith’s a plurality of recorded object attributes can be modified to be indicative of a recorded object vertical position, and the object-specific count as taught in Bordukova.
Such a modification is the result of combing prior art elements. Smith in view of Habibian and Kincaid and Bordukova share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the recorded target object is stored within a temporary object lookup structure and comprises a plurality of recorded object attributes indicative of a recorded object size, a recorded object vertical position, and the object-specific count. Thus in order to use such method for predicting of subject-related attributes with high efficacy, see Bordukova’s Par. [0003].
Regarding claim 9, Smith in view of Habibian and Kincaid and Bordukova, in combination, explicitly teaches the computer-implemented method of claim 8, wherein Smith explicitly teaches the plurality of object-specific attributes (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records”; wherein the information being recorded such as analysis of visual data including a cell type, or an analyte, present in a body fluid and more, these are analogous to the recited “recorded object attributes”) is indicative of(Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the analysis of the visual data also include information about sizes of the cell as well), and wherein the tracked target object is tracked based on at least one or more of (i) a first comparison between the recorded object size and the object size of the tracked target object, (ii) a second comparison between the recorded object vertical position and the vertical position of the tracked target object, or (iii) a third comparison based on a distance between a recorded object center point and a center point of the tracked target object (“at least one or more of…or…” indicates a selection, therefore, only one selection is required to be the instant scope of the claim, the examiner selects “wherein the tracked target object is tracked based on at least one or more of (i) a first comparison between the recorded object size and the object size of the tracked target object” to be mapped, which is taught in Smith’s Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the whole process here including applying the denoising algorithm to obtain a denoised image and filtering out based on size to obtain a filtered out image [analogous to the recited “denoised image”], and the binarizing step according to a threshold is analogous to the recited “based on a contrast threshold” [analogous to “binarizing using a specific threshold”] and the recited “corresponding to one or more shared object attributes” [analogous to “the size of each particle was analyzed in the count mask and variance” since, size and variance attribute are analogous to the disclosed shared object attributes of the instant disclosure’s Pars. 0071-0075’s consistency, since sizes of common same type of cells would share the same or similar sizes or contrast variance]).
However, Smith in view of Habibian and Kincaid, in combination, does not explicitly teach a plurality of recorded object attributes is indicative of a recorded object vertical position.
In the same field of predicting subject-related attributes (Title and Abstract, Bordukova), Bordukova explicitly teaches a plurality of recorded object attributes is indicative of a recorded object vertical position (Par. [0020] discloses “longitudinal characteristics of actual patients. With the aid of digital twins, it becomes feasible to generate entire and realistic clinical patient trajectories” moreover, Par. [0031] discloses “the clinical input comprises a medical history of a subject, the medical history comprising a plurality of values of subject-related attributes…values for at least one longitudinal attributes” therefore, the subject’s medical history including trajectories is analogous to the recited recorded object as claimed, and the longitudinal attributes is being analogous to vertical position as claimed, moreover, Par. [0006] discloses “complex, multimodal, multidimensional and longitudinal data” indicating the data can be longitudinal and multidimensional [can cover dimension in the vertical information as well, moreover, vertical position in a context can be understood to be a longitudinal position as well]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect objects to track the objects and record them based on recorded object attributes being indicative of attributes such as recorded object size, wherein the recorded object attributes include multidimensional and longitudinal attributes and blood cell count. Thus in order to use such method for predicting of subject-related attributes with high efficacy, see Bordukova’s Par. [0003]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the recorded target object is stored within a temporary object lookup structure and comprises a plurality of recorded object attributes indicative of a recorded object size. Moreover, Smith’s a plurality of recorded object attributes can be modified to be indicative of a recorded object vertical position as taught in Bordukova.
Such a modification is the result of combing prior art elements. Smith in view of Habibian and Kincaid and Bordukova share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the recorded target object is stored within a temporary object lookup structure and comprises a plurality of recorded object attributes indicative of a recorded object size, a recorded object vertical position. Thus in order to use such method for predicting of subject-related attributes with high efficacy, see Bordukova’s Par. [0003].
Regarding claim 20, Smith in view of Habibian and Kincaid, in combination, explicitly teaches the one or more non-transitory computer-readable storage media of claim 10, wherein Smith explicitly teaches wherein the recorded target object is stored within a temporary object lookup structure (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records” therefore, the recorded subject is analogous to the recited “target object” as claimed, which is the result of the process of the invention, as discussed, including the result of the tracking of the tracked target object based on the object-specific result, wherein the subject’s health records is analogous to the recited “temporary object lookup structure”) and comprises a plurality of recorded object attributes (Col. 12, lines 29-37, discloses “visual data can be analyzed using image analysis software to determine a cell type, or an analyte, present in a body fluid. Analysis of the visual data can be permanently and automatically recorded in a subject’s health records”; wherein the information being recorded such as analysis of visual data including a cell type, or an analyte, present in a body fluid and more, these are analogous to the recited “recorded object attributes”) indicative of a recorded object size (Col 24, lines 31-41, discloses “a denoising algorithm utilized an L1-norm minimization that smoothed out noise while preserving sharp edges within the image, which was necessary for identifying small and dim platelets. After applying the denoising algorithm, the image was binarized by setting a specific threshold value, and the number of platelets was counted using a count mask….the size of each particle was analyzed in the count mask…object with very large sizes were discarded filter out white cells” therefore, the analysis of the visual data also include information about sizes of the cell as well).
However, Smith in view of Habibian and Kincaid, in combination, does not explicitly teach a plurality of recorded object attributes indicative of a recorded object vertical position, and the object-specific count.
In the same field of predicting subject-related attributes (Title and Abstract, Bordukova), Bordukova explicitly teaches a plurality of recorded object attributes indicative of a recorded object vertical position (Par. [0020] discloses “longitudinal characteristics of actual patients. With the aid of digital twins, it becomes feasible to generate entire and realistic clinical patient trajectories” moreover, Par. [0031] discloses “the clinical input comprises a medical history of a subject, the medical history comprising a plurality of values of subject-related attributes…values for at least one longitudinal attributes” therefore, the subject’s medical history including trajectories is analogous to the recited recorded object as claimed, and the longitudinal attributes is being analogous to vertical position as claimed, moreover, Par. [0006] discloses “complex, multimodal, multidimensional and longitudinal data” indicating the data can be longitudinal and multidimensional [can cover dimension in the vertical information as well, moreover, vertical position in a context can be understood to be a longitudinal position as well]), and the object-specific count (Page 17 shows the list of subject-related attributes which includes blood cell count [analogous to object-specific count as claimed]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect objects to track the objects and record them based on recorded object attributes being indicative of attributes such as recorded object size, wherein the recorded object attributes include multidimensional and longitudinal attributes and blood cell count. Thus in order to use such method for predicting of subject-related attributes with high efficacy, see Bordukova’s Par. [0003]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the recorded target object is stored within a temporary object lookup structure and comprises a plurality of recorded object attributes indicative of a recorded object size. Moreover, Smith’s a plurality of recorded object attributes can be modified to be indicative of a recorded object vertical position, and the object-specific count as taught in Bordukova.
Such a modification is the result of combing prior art elements. Smith in view of Habibian and Kincaid and Bordukova share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the recorded target object is stored within a temporary object lookup structure and comprises a plurality of recorded object attributes indicative of a recorded object size, a recorded object vertical position, and the object-specific count. Thus in order to use such method for predicting of subject-related attributes with high efficacy, see Bordukova’s Par. [0003].
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) further in view of Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”) and Maria Bordukova et. al. (“US 2026/0148813 A1” hereinafter as “Bordukova”) and Tatsuo Kawanaka et. al. (“US 2021/0151169 A1” hereinafter as “Kawanaka”).
Regarding claim 10, Smith in view of Habibian and Kincaid and Bordukova, in combination, explicitly teaches the computer-implemented method of claim 9.
However, Smith in view of Habibian and Kincaid and Bordukova, in combination, does not explicitly teach wherein the plurality of recorded object attributes is indicative of an image frame length that is indicative of a number of image frames processed subsequent to a generation of the recorded target object, and wherein the computer-implemented method further comprises: modifying the temporary object lookup structure to remove the recorded target object in response to the image frame length satisfying a frame holdover threshold.
In the same field of subject health record (Title and Abstract, Kawanaka), Kawanaka explicitly teaches wherein the plurality of recorded object attributes is indicative of an image frame length that is indicative of a number of image frames (Par. [0033] discloses “performing the first test for similarity can reduce the number of images that need to be further analyzed and can therefore speed up the entire process”; moreover, Par. [0034] discloses “a reference to the specific index number of the standard image that was used to calculate the delta” indicating that each image has an index number, and the image is used to calculate a delta which is analogous to the recited “a number of image frames” being a delta value, which can be understood to be the image frame length since, Par. [0034] discloses “compress delta, which can further reduce data size” indicating the delta is correlated to data size [data length], all being the plurality of recorded object attributes, Par. [0038] discloses “the first medical image record by combining the delta with the standard image set”) processed subsequent to a generation of the recorded target object (Par. [0038] discloses “the first medical image record by combining the delta with the standard image set” indicating the delta being calculated after the creation of the medical image record and the standard image), and wherein the computer-implemented method further comprises: modifying the temporary object lookup structure to remove the recorded target object in response to the image frame length satisfying a frame holdover threshold (Par. [0038] discloses “the method can include comparing, at the workstation of the first user, the first medical image record with a standard image set to identify a similarity between the first medical image record and the standard image set…the method can include calculating, if the similarity is above a threshold and at the workstation of the first user, a delta between the first medical image record and the standard image set…the method can include transferring the delta from the workstation of the first user and to one or more computing devices having a copy of the standard image set” indicating that the delta is being compared to a threshold, to be above the threshold and transfer the medical record to another computing device [analogous to the recited limitation wherein modifying the temporary object lookup structure is transferring of the medical image set when the threshold is met to be above a certain threshold of the delta value, which as discussed previously, being analogous to the image frame length] and the threshold here is analogous to the recited “frame holdover threshold”; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have a process of recording subject’s health records based on a plurality of recorded subject’s attributes, moreover, these attributes are indicative of a delta value relating to size of data/images which is used to be compared to a threshold to determine a similarity of the currently processed medical image set to a standard set to determine if the record should be modified according to the threshold. Thus in order to use such method to reduce the number of images that need to be further analyzed and can therefore speed up the processing of images, see Kawanaka’s Par. [0033]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes. Moreover, Smith’s plurality of recorded object attributes can be modified to be indicative of an image frame length that is indicative of a number of image frames processed subsequent to a generation of the recorded target object, and wherein the computer-implemented method further comprises: modifying the temporary object lookup structure to remove the recorded target object in response to the image frame length satisfying a frame holdover threshold as taught in Kawanaka.
Such a modification is the result of combing prior art elements. Smith and Kawanaka share the same field of endeavor of subject’s record processing. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; tracking, by the one or more processors, the tracked target object from the one or more target object candidates based on the plurality of object-specific attributes; and in response to tracking the tracked target object, recording, by the one or more processors, a recorded target object corresponding to the tracked target object based on the plurality of object-specific attributes; wherein the plurality of recorded object attributes is indicative of an image frame length that is indicative of a number of image frames processed subsequent to a generation of the recorded target object, and wherein the computer-implemented method further comprises: modifying the temporary object lookup structure to remove the recorded target object in response to the image frame length satisfying a frame holdover threshold. Thus in order to use such method to reduce the number of images that need to be further analyzed and can therefore speed up the processing of images, see Kawanaka’s Par. [0033].
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Zachary Smith et. al. (“US 10,024,858 B2” hereinafter as “Smith”) in view of Amirhossein Habibian et. al. (“US 11,308,350 B2” hereinafter as “Habibian”) further in view of Robert H. Kincaid (“US 2010/0128988 A1” hereinafter as “Kincaid”) and Michael Zahniser et. al. (“US 8,339,586 B2” hereinafter as “Zahniser”).
Regarding claim 11, Smith in view of Habibian further in view of Kincaid, in combination, explicitly teaches the computer-implemented method of claim 1.
However, Smith in view of Habibian further in view of Kincaid, in combination, does not explicitly teach wherein the plurality of object-specific attributes is indicative of a center position of the tracked target object, the center position comprises one or more image coordinates corresponding to a center point of the tracked target object that are indicative of a vertical position and a horizontal position of the tracked target object.
In the same field of cell detection based on size (Title and Abstract, Zahniser), Zahniser explicitly teaches wherein the plurality of object-specific attributes is indicative of a center position of the tracked target object (Col. 17, lines 50-64, discloses “the ratio of this cell perimeter value squared to the cell area value is determined to check….cells with a ratio of the perimeter squared to the area, which exceeds the minimum value of 4pi by a threshold amount or more, are excluded from further analysis. Typically, the threshold amount is a percentage of the minimum value of 4pi” indicating the object-specific attributes used to differentiate/identify cells, moreover, Col. 17, lines 50-64, discloses “the cell perimeter is determined from the boundary pixels using the set of pixels corresponding to cell. This can be accomplished by connecting a line through the center of each perimeter pixel to create a polygon in the image and measuring the perimeter of the polygon” indicating the perimeter includes information of center position), the center position comprises one or more image coordinates corresponding to a center point of the tracked target object (Col. 17, lines 50-64, discloses “the cell perimeter is determined from the boundary pixels using the set of pixels corresponding to cell. This can be accomplished by connecting a line through the center of each perimeter pixel to create a polygon in the image and measuring the perimeter of the polygon” indicating the perimeter includes information of center position, which is used to differentiate/identify the cells) that are indicative of a vertical position and a horizontal position of the tracked target object (Col. 17, lines 50-64, discloses “the cell perimeter is determined from the boundary pixels using the set of pixels corresponding to cell. This can be accomplished by connecting a line through the center of each perimeter pixel to create a polygon in the image and measuring the perimeter of the polygon” indicating the perimeter includes information of center position, moreover, Col. 18, lines 10-24, discloses “identified cells utilizes the convex hull of the polygonal representation of the cell outline described above…FIG. 5 is a schematic diagram that includes two cells 500A and 500B” and Figure 4 and Figure 6 shows the polygon depicting the cells which is obtained according to figure 1B which includes a vertical axis [analogous to the recited vertical position] and a horizontal axis [analogous to the recited horizontal position] to identify and track cells [analogous to the recited “of the tracked target object”]; Therefore, it would have been obvious to one or ordinary skill of the art at the time the invention was made to have an object detection model that can detect objects based on center location of the object, wherein the center location includes vertical and horizontal information of the object. Thus in order to have such method of performing object identification more accurately and efficiently (Zahniser’s Abstract) using objects results to be compared and determined accuracy to perform a calibration process to improve accuracy of the method, see Zahniser’s Col. 22, lines 57-67).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Smith of a computer-implemented method with one or more object-specific attributes. Moreover, Smith’s plurality of object-specific attributes can be modified to be indicative of a center position of the tracked target object, the center position comprises one or more image coordinates corresponding to a center point of the tracked target object that are indicative of a vertical position and a horizontal position of the tracked target object as taught in Zahniser.
Such a modification is the result of combing prior art elements. Smith and Habibian and Kincaid and Zahniser share the same field of target object identification. The motivation for the proposed modification would have been to have a computer-implemented method, the computer-implemented method comprising: generating, by one or more processors, an object-specific denoised image frame for an image frame based on a contrast threshold corresponding to one or more shared object attributes for a tracked target object; generating, by the one or more processors and using an object detection model, an object matrix indicative of one or more target object candidates based on the object-specific denoised image frame; generating, by the one or more processors, a plurality of object-specific attributes for the one or more target object candidates based on the object matrix; wherein the plurality of object-specific attributes is indicative of a center position of the tracked target object, the center position comprises one or more image coordinates corresponding to a center point of the tracked target object that are indicative of a vertical position and a horizontal position of the tracked target object. Thus in order to have such method of performing object identification more accurately and efficiently (Zahniser’s Abstract) using objects results to be compared and determined accuracy to perform a calibration process to improve accuracy of the method, see Zahniser’s Col. 22, lines 57-67.
Pertinent Prior Art(s)
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Geneslaw, Luke et. al., “US 12555672 B2”, discloses a computing system having one or more processors coupled with memory may identify, from a data source, a biomedical image having a first plurality of pixels in a first color representation. The computing system may convert the first plurality of pixels from the first color representation to a second color representation to generate a second plurality of pixels. The computing system may identify, from the second plurality of pixels, a subset of pixels having a color value satisfying a threshold value. The computing system may detect the biomedical image as having at least one label based at least on a number of pixels in the subset of pixels satisfying a threshold count. The computing system may store, in one or more data structures, an indication for the biomedical image as having the at least one label.
Benaron, David A, “US 2012/0133749 A1”, discloses A device for determining the presence, absence, concentration, or count of rare cell or cell-like objects in a turbid fluid consisting of a light source for illuminating a chamber containing a solution including complexes of suspended cells or cell-like moieties and an optically-active agent, and further including an imaging detector and an output for providing a determined or displayed result. Methods of enumeration are also disclosed.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHUONG HAU CAI whose telephone number is (571)272-9424. The examiner can normally be reached M-F 8:30 am - 5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Chineyere Wills-Burns can be reached at (571) 272-9752. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PHUONG HAU CAI/ Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights