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 .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-7 and 9-10 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Re claim 1
The limitation of” output a mask indicating an area of an object included in an image and a detection score indicating detection accuracy of the area, based on the image and a prompt”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, output a mask in the context of this claim encompasses a user mentally envisioning a mask.
The limitation of “output…the area of the object from the image, based on the mask and the detection score”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining the context of this claim encompasses the mentally determining an area to clip of the output image.
The limitation of identify a category of the object based on the clipped image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, identifying in the context of this claim encompasses the user identifying an area of the image to be clipped.
The limitation of output the area of the object and the category of the object, as an object detection result, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, outputting in the context of this claim encompasses the user mentally outputting the results.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements – An object detection device comprising: a memory configured to store instructions; and a processor configured to execute the instructions and output a clipped image obtained by clipping the area of the object from the image. The processor and memory in the steps is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of ranking information based on a determined amount of use) such that it amounts no more than mere instructions to apply the exception using a generic computer component. The language “output a clipped image obtained by clipping the area of the object from the image” is a well known process of cropping an object of an image (see Kuberka US 20080298796 A1.) Accordingly, these additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor and memory to perform the steps amounts to no more than mere instructions to apply the exception using a generic computer component. The language “output a clipped image obtained by clipping the area of the object from the image” is a well known process of cropping an object of an image (see Kuberka US 20080298796 A1.) Mere instructions to apply an exception using a generic computer component and performing the well known process of cropping cannot provide an inventive concept. The claim is not patent eligible.
Re claim 2 The limitation of “integrate a plurality of masks corresponding to a same object to generate an integrated mask, based on the mask and the detection score,” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, integrating the masks in the context of this claim encompasses the user mentally integrating the masks.
The limitation of “ the area of the object using the integrated mask”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining the area in the context of this claim encompasses the user mentally determining an area of the image to clip.
The analysis with respect to integration into a practical application and significantly more are not significantly different from the claim which this claim depends.
Re claim 3 The limitation of “the image along a shape of the integrated mask”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining an image along a shape of the mask in the context of this claim encompasses the user determine a portion of the image to clip.
The analysis with respect to integration into a practical application and significantly more are not significantly different from the claim which this claim depends.
Re claim 4 The limitation of “the image along a rectangle surrounding the integrated mask”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining an image along a rectangle surrounding the integrated mask in the context of this claim encompasses the user determine a portion of the image to clip.
The analysis with respect to integration into a practical application and significantly more are not significantly different from the claim which this claim depends.
Re claim 5 The limitation of “the image along a shape larger than the integrated mask.”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, the image along a shape larger than the integrated mask in the context of this claim encompasses the user determine a portion of the image to clip.
The analysis with respect to integration into a practical application and significantly more are not significantly different from the claim which this claim depends.
Re claim 6 the limitation of “outputs an identification score indicating identification accuracy of the category of the object” and “outputs the identification score as the object detection result”
as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, outputs identification score and outputting the identification score as a result in the context of this claim encompasses the user mentally determining an identification score and mentally outputting this score as a result.
The analysis with respect to integration into a practical application and significantly more are not significantly different from the claim which this claim depends.
Re claim 7
The limitation of another object detection different from the object detection, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, performing another object detection in the context of this claim encompasses the user mentally performing an additional object detection
The limitation of integrate a first object detection result output by the object detection device and a second object detection result output by the another object detection device to output a third object detection result, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, integrating results in the context of this claim encompasses the user mentally performing the integration
The analysis with respect to integration into a practical application and significantly more are not significantly different from the claim which this claim depends.
Re claim 9
The limitation of” outputting a mask indicating an area of an object included in an image and a detection score indicating detection accuracy of the area, based on the image and a prompt”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, output a mask in the context of this claim encompasses a user mentally envisioning a mask.
The limitation of “ outputting…the area of the object from the image, based on the mask and the detection score”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining the context of this claim encompasses the mentally determining an area to clip of the output image.
The limitation of identify a category of the object based on the clipped image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, identifying in the context of this claim encompasses the user identifying an area of the image to be clipped.
The limitation of outputing the area of the object and the category of the object, as an object detection result, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, outputting in the context of this claim encompasses the user mentally outputting the results.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements –output a clipped image obtained by clipping the area of the object from the image. The language “output a clipped image obtained by clipping the area of the object from the image” is a well known process of cropping an object of an image (see Kuberka US 20080298796 A1.) Accordingly, these additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application the language “output a clipped image obtained by clipping the area of the object from the image” is a well known process of cropping an object of an image (see Kuberka US 20080298796 A1.) Mere instructions to perform the well known process of cropping cannot provide an inventive concept. The claim is not patent eligible.
Re claim 10
The limitation of” outputing a mask indicating an area of an object included in an image and a detection score indicating detection accuracy of the area, based on the image and a prompt”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, output a mask in the context of this claim encompasses a user mentally envisioning a mask.
The limitation of “outputting the area of the object from the image, based on the mask and the detection score”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, determining the context of this claim encompasses the mentally determining an area to clip of the output image.
The limitation of identify a category of the object based on the clipped image, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, identifying in the context of this claim encompasses the user identifying an area of the image to be clipped.
The limitation of output the area of the object and the category of the object, as an object detection result, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, outputting in the context of this claim encompasses the user mentally outputting the results.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements – A non-transitory computer-readable recording medium storing a program, the program causing a computer to execute processing of and output a clipped image obtained by clipping the area of the object from the image. The non-transitory computer-readable recording medium (i.e., as non-transitory computer-readable recording medium performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. The language “output a clipped image obtained by clipping the area of the object from the image” is a well known process of cropping an object of an image (see Kuberka US 20080298796 A1.) Accordingly, these additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor and memory to perform the steps amounts to no more than mere instructions to apply the exception using a generic computer component. The language “output a clipped image obtained by clipping the area of the object from the image” is a well known process of cropping an object of an image (see Kuberka US 20080298796 A1.) Mere instructions to apply an exception using a generic computer component and performing the well known process of cropping cannot provide an inventive concept. The claim is not patent eligible
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-4, 6, 9, and 10 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by IInuma US 20260080652 A1.
Re claim 1 IInuma discloses
An object detection device comprising: a memory configured to store instructions (see paragraph 87 note that the program may be stored in memory); and a processor (see paragraph 86 note that the processor may execute the program) configured to execute the instructions to:
output a mask indicating an area of an object included in an image (see paragraph 54 a plurality of candidate rectangles are extracted based on clusters of objects which are reliable ) and a detection score indicating detection accuracy of the area (see paragraph 54 and 65 note that reliability of clusters are used determine the candidate rectangles further a density score and priority score are used to select rectangles ), based on the image (see paragraph 54 and figure 3 note that the rectangle extraction unit is based on a video input ) and a prompt ( see paragraph 55 “the rectangle selection unit 112 selects a rectangle to which the object detection is applied by using the result of density estimation and the rectangle selected in the past frame from among the candidate rectangles extracted by the rectangle extraction unit 110” note that information from past frames could be considered a prompt);
output a clipped image obtained by clipping the area of the object from the image (see paragraph 68 note that rectangles which are selected are cut out i.e. clipped), based on the mask and the detection score (see paragraph 54 note that candidate rectangles are selected whose reliability is equal to or more than a fixed value see paragraph 55 note particular rectangles are selected);
identify a category of the object based on the clipped image (see paragraph 56 note that an object detection model is applied to the rectangles and class reliability and the bounding box in the image is output); and output the area of the object and the category of the object, as an object detection result (see paragraph 56 note that an object detection model is applied to the rectangles and class reliability and the bounding box in the image is output).
Re claim 2 IInuma discloses integrate a plurality of masks corresponding to a same object to generate an integrated mask (see paragraph 54 and 55 note that the multiple rectangles are extracted and highest priority rectangles are selected), based on the mask and the detection score (see paragraphs 64-68 and figure 6 note that rectangles a selected by a rectangle selection process where in the highest rectangles are selected based on a density score and an overlap score), and wherein the processor clips the area of the object using the integrated mask (see paragraph 68 and figure 6 note that the selected rectangles are cut out).
Re claim 3 IInuma discloses wherein the processor clips the image along a shape of the integrated mask (see paragraph 68 note that mask is a rectangle and the rectangle is cut out i.e. along the shape of the mask).
Re claim 4 IInuma discloses wherein the processor clips the image along a rectangle surrounding the integrated mask. (see paragraph 68 note that mask is a rectangle and the rectangle is cut out i.e. along the shape of the mask).
Re claim 6 IInuma discloses an identification score indicating dentification accuracy of the category of the object, and wherein the processor further outputs the identification score as the object detection result (see paragraph 56 note that the a class, reliability [i.e identification accuracy], and a bounding box of the object included in the input image is provided as an output).
Re claim 9 IInuma discloses
An object detection method comprising
outputting a mask indicating an area of an object included in an image (see paragraph 54 a plurality of candidate rectangles are extracted based on clusters of objects which are reliable ) and a detection score indicating detection accuracy of the area (see paragraph 54 and 65 note that reliability of clusters are used determine the candidate rectangles further a density score and priority score are used to select rectangles ), based on the image (see paragraph 54 and figure 3 note that the rectangle extraction unit is based on a video input ) and a prompt ( see paragraph 55 “the rectangle selection unit 112 selects a rectangle to which the object detection is applied by using the result of density estimation and the rectangle selected in the past frame from among the candidate rectangles extracted by the rectangle extraction unit 110” note that information from past frames could be considered a prompt);
outputting a clipped image obtained by clipping the area of the object from the image (see paragraph 68 note that rectangles which are selected are cut out i.e. clipped), based on the mask and the detection score (see paragraph 54 note that candidate rectangles are selected whose reliability is equal to or more than a fixed value see paragraph 55 note particular rectangles are selected);
identifying a category of the object based on the clipped image (see paragraph 56 note that an object detection model is applied to the rectangles and class reliability and the bounding box in the image is output); and outputting the area of the object and the category of the object, as an object detection result (see paragraph 56 note that an object detection model is applied to the rectangles and class reliability and the bounding box in the image is output).
Re claim 10 IInuma discloses
A non-transitory computer-readable recording medium storing a program, the program causing a computer to execute processing of (see paragraph 87 note that the program may be stored in memory see paragraph 86 note that the processor may execute the program)
output a mask indicating an area of an object included in an image (see paragraph 54 a plurality of candidate rectangles are extracted based on clusters of objects which are reliable ) and a detection score indicating detection accuracy of the area (see paragraph 54 and 65 note that reliability of clusters are used determine the candidate rectangles further a density score and priority score are used to select rectangles ), based on the image (see paragraph 54 and figure 3 note that the rectangle extraction unit is based on a video input ) and a prompt ( see paragraph 55 “the rectangle selection unit 112 selects a rectangle to which the object detection is applied by using the result of density estimation and the rectangle selected in the past frame from among the candidate rectangles extracted by the rectangle extraction unit 110” note that information from past frames could be considered a prompt);
output a clipped image obtained by clipping the area of the object from the image (see paragraph 68 note that rectangles which are selected are cut out i.e. clipped), based on the mask and the detection score (see paragraph 54 note that candidate rectangles are selected whose reliability is equal to or more than a fixed value see paragraph 55 note particular rectangles are selected);
identify a category of the object based on the clipped image (see paragraph 56 note that an object detection model is applied to the rectangles and class reliability and the bounding box in the image is output); and output the area of the object and the category of the object, as an object detection result (see paragraph 56 note that an object detection model is applied to the rectangles and class reliability and the bounding box in the image is output).
Claim Rejections - 35 USC § 103
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.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over IInuma US 20260080652 A1 in view of Pham US 2021/0319255.
Re claim 5 IInuma further disclose wherein the processor clips the image along a shape of the integrated mask (see paragraph 68 note that mask is a rectangle and the rectangle is cut out i.e. along the shape of the mask). IInuma does not expressly disclose clips the image along a shape larger than the integrated mask. In a similar field of endeavor, Pham discloses clips the image along a shape larger than the integrated mask. (See paragraph 162 “the object selection system 106 can enlarge the size of the input bounding box 612 as part of generating the cropped image 616. For example, as shown, the object selection system 106 enlarges the input bounding box 612 of the region proposal to create an enlarged bounding box 614 (i.e., enlargement of the approximate boundary), and as a result, an enlarged cropped image 618”). The motivation to combine is “In many implementations, enlarging the bounding box provides additional context information to the auto tagging model 600 to better recognize and classify detected objects within the enlarged cropped image 61” see paragraph 162. One of ordinary skill in the art could have enlarged the bounding boxes of IInuma to add additional context for the object recognition and classification as described in Pham. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine IInuma and Pham to reach the aforementioned advantage.
Claim(s) 7 and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over IInuma US A1 in view of Wang WO2023077821A1.
Re claim 7 IInuma discloses the object detection device according to claim 1 including the processor and memory (see rejection to claim 1);
IInuma does not expressly disclose and another object detection device different from the object detection device, integrate a first object detection result output by the object detection device and a second object detection result output by the another object detection device to output a third object detection result.
In a similar field of endeavor Wang discloses another object detection device different from the object detection device, (see paragraph 45 note that multiple models are used to generate labels of objects and coordinates)
integrate a first object detection result output by the object detection device and a second object detection result output by the another object detection device to output a third object detection result see paragraph 45 “Then, the four coordinates generated by the models under the three parameters were weighted and fused to obtain the final coordinates (x<sub>1</sub>, y<sub>1</sub>, x<sub>2</sub>, y<sub>2</sub>). The label with the highest probability, y<sub>c</sub>, was selected as the final class label. Thus, y’ = (x<sub>1</sub>, y<sub>1</sub>, x<sub>2</sub>, y<sub>2</sub>) + y<sub>c</sub> was added to the training set as the final pseudo-label.” Note the coordinates and labels output by the different detectors are fused to create a final label and coordinates). The motivation to combine is “The main purpose is to obtain more realistic annotation information for unlabeled data, increase the effective information content of the dataset, and finally train all the data together to obtain the final test model parameters.” (see paragraph 46) One of ordinary skill in the art could have used a process similar to that of Wang to train object detectors similar to IInuma to using more realistic annotation information for unlabeled data, and increase the effective information content of the dataset. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Wang and IInuma to reach the aforementioned advantage.
Re claim 8 IInuma discloses the object detection device according to claim 1 including the processor and memory (see rejection to claim 1);
IInuma does not expressly disclose and another object detection device different from the object detection device, integrate a first object detection result output by the object detection device and a second object detection result output by the another object detection device to output a third object detection result; and train the another object detection device using the third object detection result as training data
In a similar field of endeavor Wang discloses another object detection device different from the object detection device, (see paragraph 45 note that multiple models are used to generate different labels of objects and coordinates).
Integrate a first object detection result output by the object detection device and a second object detection result output by the another object detection device to output a third object detection result see paragraph 45 “Then, the four coordinates generated by the models under the three parameters were weighted and fused to obtain the final coordinates (x<sub>1</sub>, y<sub>1</sub>, x<sub>2</sub>, y<sub>2</sub>). The label with the highest probability, y<sub>c</sub>, was selected as the final class label. Thus, y’ = (x<sub>1</sub>, y<sub>1</sub>, x<sub>2</sub>, y<sub>2</sub>) + y<sub>c</sub> was added to the training set as the final pseudo-label.” Note the coordinates and labels output by the different detectors are fused to create a final label and coordinates); and train the another object detection device using the third object detection result as training data (see paragraph 46 “The self-training process described above requires a total of 6 iterations. The main purpose is to obtain more realistic annotation information for unlabeled data, increase the effective information content of the dataset, and finally train all the data together to obtain the final test model parameters” note that the pseudo label is used to train a final model)
The motivation to combine is “The main purpose is to obtain more realistic annotation information for unlabeled data, increase the effective information content of the dataset, and finally train all the data together to obtain the final test model parameters.” (see paragraph 46) One of ordinary skill in the art could have used a process similar to that of Wang to train object detectors similar to IInuma to using more realistic annotation information for unlabeled data, and increase the effective information content of the dataset. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Wang and IInuma to reach the aforementioned advantage.
Cited Art
The following is a listing of prior art considered relevant but not recited in a rejection above:
UZAWA US 20250329128 A1 discloses:
An object detection device that detects an object from an image included in a moving image includes: an acquisition unit configured to acquire the image from the moving image; a number-of-faces setting unit configured to set a number of faces for dividing the image into a plurality of partial faces using a difference between consecutive images; an allocation control unit configured to allocate a frequency of detecting the object for each of the divided partial faces; a division processing unit configured to divide the image into a plurality of partial faces depending on the set number of faces and to detect an object from the partial faces in accordance with the allocated frequency; an overall processing unit configured to reduce the image to an entire face indicating the entire image and to detect an object from the entire face; and a combination processing unit configured to combine respective detection results detected from the partial faces and the entire face to detect an object from the image. (see abstract)
SHIBATA US 20220327813 A1 discloses A learning apparatus (500) according to the present invention includes a detection unit (510) that detects, as a candidate region of a learning target, a region detected by one of first detection processing of detecting an object region from a predetermined image and second detection processing of detecting a change region from background image information and the image, and not detected by the other, an output unit (520) that outputs at least a part of the candidate region as a labeling target, and a learning unit (530) that learns a model for performing the first detection processing or a model for performing the second detection processing by using the labeled candidate region as learning data. (see abstract)
Yu US 20200394458 A1 discloses FIG. 6A illustrates an example process 600 for training a neural network, such as a generative adversarial network (GAN), to infer object detections and/or segmentations in at least one embodiment. It should be understood for this and other processes discussed herein that there can be additional, alternative, or fewer steps performed in similar or alternative orders, or in parallel, in at least one embodiment unless otherwise stated. Further, this example discusses training a generative adversarial network (GAN) using alphanumeric semantic description data, but as discussed elsewhere herein there can be various types of models trained using a variety of different types of data within a scope of at least one embodiment. In at least one embodiment, an image (or video frame, etc.) is obtained 602 that includes at least one representation of an object type of interest, with an image including one or more image-level labels indicating one or more classes of objects represented in an image. In at least one embodiment, labeling may not include any location or instance data, etc. In at least one embodiment a set of object proposals can be determined, either external or internal to a neural network, such as a GAN in this example. In at least one embodiment object proposal regions can be input to a detection branch of a GAN, which as discussed elsewhere herein can determine a region of interest (ROI) score or similar such value for various proposals, and in at least one embodiment can reduce a number of proposals based at least in part upon determined scores. In at least one embodiment ROI scores for various proposals can be passed to one or more refinement branches of a network that can determine 606 pseudo-labels for various proposals. In at least one embodiment these pseudo-labels can be associated with new or updated ROI scores for various proposals as determined using criteria or approaches for relevant refinement branches. In at least one embodiment, an ROI score from an object detection branch is combined 608 with pseudo-label scores from refinement branches to generate a set of final ROI scores for various proposals and classes. In at least one embodiment a loss function can be determined 610 using a set of final ROI scores. Network parameters for a GAN can then be updated 612 based at least in part upon a determined loss function (paragraph 61 )
Shen US 20200175326 A1 discloses Systems and methods for enhanced object detection for autonomous vehicles based on field of view. An example method includes obtaining an image from an image sensor of one or more image sensors positioned about a vehicle. A field of view for the image is determined, with the field of view being associated with a vanishing line. A crop portion corresponding to the field of view is generated from the image, with a remaining portion of the image being downsampled. Information associated with detected objects depicted in the image is outputted based on a convolutional neural network, with detecting objects being based on performing a forward pass through the convolutional neural network of the crop portion and the remaining portion. (see abstract)
EL-KHAMY US 20180089505 A1 disclsoes A method and apparatus are provided. The method includes receiving an image, detecting an object in the image, determining, by a primary object detector, a primary confidence detection score of the object, determining, by a classification network, a confidence scaling factor of the object, and adjusting the primary confidence detection score based on multiplying the primary confidence detection score by the confidence scaling factor. (see abstract)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN T MOTSINGER whose telephone number is (571)270-1237. The examiner can normally be reached 9AM-5PM.
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.
/SEAN T MOTSINGER/Primary Examiner, Art Unit 2673
Prosecution Insights