DETAILED ACTION
The amendments received on 07/31/2026 are entered for consideration. Claims 1, 4, 5, 9, and 10 have been amended. Claims 2 and 3 have been canceled. Claims 1 and 4-10 remain pending. The new grounds of rejection in the office action have been necessitated by applicants’ amendments. Therefore, this Action is made FINAL.
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 .
Priority
The present application is a 371 continuation of international PCT/JP2022/046676 filed on October 21, 2022, and claims benefit of the foreign application JP 2021-215451 filed on 12/29/2021.
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on 07/15/2026 and 07/01/2024, with the exception of foreign application JP 2022-160363 A submitted with the IDS filed on 07/01/2024, is in compliance with the provisions of 37 CFR 1.97. There was no English translation of the JP 2022-160363 A reference in its entirety and/or subsections of relevant passages. Accordingly, the information disclosure statements, with the exception of JP 2022-160363 is being considered by the examiner.
Response to Arguments
In total, claims 1, 4, 5, 9, and 10 have been amended.
Applicant amended independent claim 1 to incorporate limitations based on canceled claims 2 and 3, including limitations directed to the detector outputting attribute information including information on positions of the objects and information on outer shapes of the objects, and the selector creating a target model corresponding to the target in the image based on the attribute information of the object selected as the target. Claim 10 has been amended in a corresponding manner.
In the remarks and claims filed on 07/31/2026, Applicant indicated claim 9 was amended. Examiner notes claim 9 appears not to have been amended since the non-final action was mailed on 04/03/2026 because the claim recites the same language, and despite the claim being labeled “Currently Amended,” the claim includes no indication of amended claim language, such as underlined words, lined out words, or the like. For clarity, it appears claim 9 was amended during the preliminary amendments. Also, the submitted applicant remarks did not indicate claim 4 being amended and the submitted amended claim set reads “Original,” next to claim 4. However, the submitted amended claims indicate claim 4 was amended to change dependency upon claim 1, rather than canceled claim 2, reciting “The object detector according to claim 1.” Accordingly, the amendment to claim 4, is entered.
Claims 2-3 are canceled, and claims 1 and 4-10 are pending.
Regarding the 101 rejections,
Applicant argues the amended claim 1 is not directed to an abstract idea because the claim “integrates any alleged idea into a practical application.” In summary, Applicant argues the amended claim is patent eligible under Step 2A, Prong Two, because it recites a particular configuration/technical arrangement that is a practical application of image-processing technology that improves object detection, rather than merely reciting a result to be achieved. Page 4 through 5 of the Applicant’s remarks goes on to describe the particular configuration of amended claim 1, including “As amended, claim 1 recites a first detector including a detector and a selector. The detector detects objects included in an image by using a detection model trained by machine learning, and outputs, as a detection result of the objects, attribute information including information on positions of the objects and information on outer shapes of the objects. The selector selects an object as the target from the detected objects and creates a target model corresponding to the target in the image based on the attribute information of the object selected as the target. The setter sets a search area based on the target detected by the first detector. A second detector then detects the target by performing a matching process based on the search area of the image.” Applicant then goes on to explicitly cite different benefits of the configuration throughout amended claim 1, and how the configuration addresses problems associated with image-based object detection, including “excessive processing time, reduced matching efficiency, and imperfect preliminary detection accuracy.” For example, Applicant explains the matching process based on the detection result performed by the detection model allows for template images corresponding to various types of objects included in an image to be appropriately created because the template is based on the detection result, thereby “facilitating the matching process and increasing matching accuracy,” unlike models that rely on prepared models, which struggle or fail to account for various types of objects. Applicant also argues claim 10 is patent eligible for reasons corresponding to those discussed above for claim 1.
Examiner notes, the paragraphs cited in section II of the Applicant remarks filed on 07/31/2026 and found on p. 5, such as paragraphs ¶¶ [0065]-[0067], ¶ [0068], and ¶ [0069], do not correspond to the correct sections/paragraphs of the specification submitted on 07/01/2024. However, upon further consideration, Examiner was able to locate the corresponding configurations and their respective benefits Applicant described in their remarks. For example, the two-stage controller detections are described in at least ¶ [0054] of the specification, not ¶¶ [0065]-[0067]; the specific significance of the target model described in the remarks is found in at least ¶ [0057] of the specification, not ¶ [0068]; and, the template image for the matching process that can be created based on the detection result by the detection model is found in at least ¶ [0058] of the specification, not ¶ [0069].
Nevertheless, these arguments are consistent with the discussion between the Applicant and Examiner held on 07/30/2026. Examiner finds the applicant’s arguments that the configuration of amended claims 1 and 10, and its benefits in addressing technological problems associate with object detection, to be persuasive in that the amended claim integrates the judicial exception into a practical application. Accordingly, the 35 U.S.C. 101 rejections for claims 1, 10, and their dependent claims 2-8 are withdrawn.
Regarding the 103 rejections,
Applicant and the Examiner discussed the proposed amendments during an interview held on 07/28/2026. During the course of the interview, Applicant explained the proposed amendments to claim 1 were distinguishable from the Tomotaka (JP 2020107142 A) prior art reference cited in the non-final mailed on 04/03/2026 for the same reasons addressed in the Applicant’s remarks filed on 07/31/2026. Examiner found the proposed amendments and the Applicant’s arguments to be persuasive in overcoming the prior-art rejections.
Specifically, Examiner finds the amended claim 1 to be distinguishable from Tomotaka at least because Tomotaka does not explicitly disclose or suggest the claimed creation of a target model corresponding to the target in the image based on the attribute information of the object selected as the target because Tomotaka discloses selecting an appropriate template from among a plurality of templates and performing a pattern matching using the selected template (see at least Tomotaka ¶ [0022], ¶¶ [0042]-[0044], ¶¶ [0052]-[0053]), rather than creating a target model generated from the detection information for the particular selected target instance. Applicant also argues the claimed target model is not merely a frame, bounding box, limited range, or selected stored template, as taught by Tomotaka (Tomotaka paragraph 40).
Applicant further argues Yang (US 20160210525 A1) fails to cure the deficiencies discussed above and since Claim 10 has been amended to recite corresponding object-detection program functionality discussed with respect to claim 1, the rejections under 35 U.S.C. 102 and 103 should be withdrawn.
Applicant’s arguments, see section III on p. 6-7, filed on 07/31/2026, with respect to the rejection(s) of claim(s) 1-10 under 35 U.S.C. 102(a)(1) and 103 have been fully considered and are persuasive. Therefore, the rejections have been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Cavallaro (US 20090028385 A1).
In summary, claims 1 and 10 were previously rejected under 35 U.S.C. 102(a)(1) as being anticipated by Tomotaka. However, the new grounds of rejections for claims 1-10 are 35 U.S.C. 103 obvious rejections, as seen in 35 U.S.C. 103 rejection section below, wherein Cavallaro is relied upon for the distinguishing operations between the amended claim and previously relied upon Tomotaka. While Tomotaka selects a template corresponding to a target from a plurality of previously prepared templates, Cavallaro teaches determining an estimated location, size, and orientation of a representation of a particular object in an image and defining a template based on the estimated location, size, and orientation of the object. Cavallaro further teaches that the template may be obtained by rendering a model of the object at the estimated location and orientation and determining a search area around the rendered model (Cavallaro ¶ [0111]). Cavallaro also teaches establishing a bounding region according to the estimated size of the representation of the object in the image and establishing a larger search area extending around the bounding region (Cavallaro ¶ [0058]-[0059]). Thus, the rejection does not rely on Tomotaka’s selection of a previously prepared template as constituting the claimed creation of the target model. Rather, Cavallarao is relied upon for teaching creation of an object-specific model based on information characterizing the location and outer dimensions of the particular object in the image and establishing a search area around that model. See the new grounds of a 35 U.S.C. 103 rejection under Tomotaka, in view of Cavallaro, discussed in the 35 U.S.C. 103 section below.
Examiner’s Note: Original claim 3 included the language, inter alia, of: “…wherein the detector outputs information on positions of the objects and information on outer shapes of the objects, as a detection result of the objects, the selector creates a target model corresponding to the target in the image, based on the information on the position and the information on the outer shape of the object selected as the target….”
Amended claims 1 and 10 include the amended language: “wherein the detector outputs, as a detection result of the objects, attribute information including information on positions of the objects and information on outer shapes of the objects, wherein the selector creates a target model corresponding to the target in the image based on the attribute information of the object selected as the target…”
The addition of the previously-unclaimed “attribute information” is understood to change the scope of the amended claims such that the reliance on new reference Cavallaro (US 20090028385 A1) is appropriate.
Regarding Objection to Specification,
The specification was objected to because the Abstract “reads as extensive mechanical or design details, and/or claim language, rather than a narrative form that describes the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent for text details” (p. 3 of Non-final Office Action mailed on 04/03/2026). No amendment and/or argument was received by the Examiner with respect to the Abstract and the objection by the Examiner. Therefore, the objection to the specification remains, as seen below.
Specification
Applicant is reminded of the proper content of an abstract of the disclosure.
A patent abstract is a concise statement of the technical disclosure of the patent and should include that which is new in the art to which the invention pertains. The abstract should not refer to purported merits or speculative applications of the invention and should not compare the invention with the prior art.
If the patent is of a basic nature, the entire technical disclosure may be new in the art, and the abstract should be directed to the entire disclosure. If the patent is in the nature of an improvement in an old apparatus, process, product, or composition, the abstract should include the technical disclosure of the improvement. The abstract should also mention by way of example any preferred modifications or alternatives.
Where applicable, the abstract should include the following: (1) if a machine or apparatus, its organization and operation; (2) if an article, its method of making; (3) if a chemical compound, its identity and use; (4) if a mixture, its ingredients; (5) if a process, the steps.
Extensive mechanical and design details of an apparatus should not be included in the abstract. The abstract should be in narrative form and generally limited to a single paragraph within the range of 50 to 150 words in length.
The abstract of the disclosure is objected to because it reads as extensive mechanical or design details, and/or claim language, rather than a narrative form that describes the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent for text details.
A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text.
See MPEP § 608.01(b) for guidelines for the preparation of patent abstracts.
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 limitations 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 do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “a first detector,” “a setter,” “a second detector,” “a detector,” “a selector,” in claim 1, “a detector” and “a robot controller” in claim 9.
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.
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 (i.e., changing from AIA to pre-AIA ) 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, 5-6, 8-10 are rejected under 35 U.S.C. 103 as being unpatentable over Tomotaka (JP 2020107142 A; paragraph numbers correspond to machine translated copy provided by applicant in IDS, see corresponding FIGs in original copy provided by applicant in the IDS) in view of Cavallaro (US 20090028385 A1).
Regarding claim 1 (Currently Amended),
Tomotaka teaches: An object detector (Tomotaka teaches “recognition method, a recognition system” (¶ [0001]), including a recognition unit (¶ [0007]).) comprising:
a first detector that detects a target from an image including objects, by using a detection model trained by machine learning, the first detector including a detector that detects objects included in the image, by using the detection model, and a selector that selects an object as the target from the objects detected by the detector (Tomotaka teaches “the first recognition process (first recognition unit 11) recognizes the type of the target object 51 and the position of the target object 51 in the image D 1 as the first feature of the target object 51” using a classifier “obtained by machine learning,” using neural networks or “a classifier generated by deep learning using a multilayer neural network” (¶ [0034]), and further teaches use of trained neural networks, such as CNNs or BNN (¶ [0035]). Tomotaka further teaches that the first recognition process recognizes “one or more” items among the multiple items in image data D1 and identifies their type and position (¶ [0040]). Regarding the selection of the target, Tomotaka teaches that, “In a case where a plurality of target objects 51 are recognized by the first recognition unit 11, the second recognition unit 12 selects the template Tl corresponding to the type of the target object 51 located at a position where the robot 3 can easily pick the target object 51 from among the plurality of target objects 51” ([0052]). Thus, Tomotaka identifies from among the objects recognized by the first recognition unit, the particular object subjected to the subsequent recognition and picking operation based on its position, thereby teaching selecting an object as the target from the detected objects.);
a setter that sets, as a search area, an area that includes the target detected by the first detector from the image and is larger than the target; a second detector that detects the target by performing a matching process based on the search area of the image (Tomotaka teaches that the second recognition unit “limits a range” in which template T1 is applied based on the first feature recognized by the first recognition process, wherein the range is, for example, the “frame B1 surrounding the target object 51” (¶ [0043]). Tomotaka further teaches that the second recognition unit “performs pattern matching in a range (for example, a frame Bl illustrated in FIG. 3) including the position of the target object 51” (¶ [0053]). Because frame B1 surrounds/encloses the object recognized by the first recognition process (¶ [0040]; ¶ [0043]), frame B1 teaches a search area that includes the target detected by the first detector and is larger than the target.
Tomotaka also teaches selecting “one recognition unit 121 from the plurality of recognition units 121 according to at least the first feature recognized” (¶ [0041]), and selecting “a template Tl corresponding to the target object 51 from the plurality of templates Tl in accordance with the type of the target object 51 recognized in the first recognition process” and performing pattern matching using the selected template (¶ [0042]). Thus, Tomotaka’s second recognition unit corresponds to the claimed second detector because it selects a template corresponding to the object recognized by the first detector and detects that object by performing pattern matching using the selected template within frame B1, which is a search area that includes the object detected by the first detector and is larger than the object.)
wherein the detector outputs, as a detection result of the objects, attribute information including information on positions of the objects and information on outer shapes of the objects (Tomotaka teaches that the first features of the target object 51 recognized during the first recognition process may include “the type, shape, size, and pattern of the target object 51, the color distribution in the target object 51…” and “the position of the target object 51 in the image D1” (¶ [0019]). Tomotaka further teaches that the first recognition process recognizes one or more items, identifies the type of each recognized item, and recognizes its position coordinates (¶ [0040]). Thus, Tomotaka’s first recognition unit provides, as its recognition/detection result, object attribute information including position and shape information, wherein the expressly recognized “shape” reasonably corresponds to information on the claimed “outer shape” because the claim does not require the outer-shape information to be represented in a particular form.).
Although Tomotaka teaches selecting template T1 corresponding to the selected/recognized object according to its first feature, Tomotaka’s recognition means/templates are prestored in the memory (¶ [0041]), and the template T1 is selected “from the plurality of templates T1” (¶ [0042]). Thus, Tomotaka does not explicitly disclose creating the target model corresponding to the selected target in the image based on the attribute information resulting from detection of that particular object, as claimed and highlighted by the Applicant throughout the interview with the Examiner and throughout their remarks/response to the non-final office action.
Therefore, Tomotaka fails to explicitly disclose: wherein the selector creates a target model corresponding to the target in the image based on the attribute information of the object selected as the target, and wherein the setter sets, as the search area, an area that includes the target model in the image and is larger than the target model.
In a related art, Cavallaro teaches: wherein the selector creates a target model corresponding to the target in the image based on the attribute information of the object selected as the target, and wherein the setter sets, as the search area, an area that includes the target model in the image and is larger than the target model (Cavallaro teaches that “Once the object is detected in the image, the pixel data which represents the object can be stored as a template 300 for use in detecting the object in a subsequent image,” that the template can “conform to the shape of the object,” and the “template can be determined automatically from the detected position of an object in an image” (¶ [0061]). Thus, Cavallaro teaches creating a target model corresponding to the detected target based on detected attribute information of the particular object, including its position and shape.
Cavallaro further teaches that “The template 700 and other templates discussed herein can be generated on the fly for each tracked object” (¶ [0080]), and teaches detecting a representation of the object and “storing pixel data of the representation of the object as a template for future use” (¶ [0117]). Thus, Cavallaro teaches creating an object-specific target model corresponding to the particular target, rather than merely selecting a previously stored template (as previously taught by Tomotaka).
Cavallaro further teaches “defining the search area based on the size and location of the template” and “the search area can be determined around the rendered model” (¶ [0111]). Cavallaro further teaches that search area 210 “extends a specified number of pixels around the bounding box, e.g., above, below, to the right and to the left” (¶ [0058]). Thus, Cavallaro teaches setting, as the search area, an area that includes the target model in the image and is larger than the target model.
Tomotaka and Cavallaro are analogous art because they’re both directed to object detection and/or recognition and each teaches techniques of limiting or defining an area in which subsequent object detection or recognition processing is performed.
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Tomotaka’s machine-learning-based object detection and subsequent template-matching system according to the teachings of Cavallaro to create an object-specific target model from the detected attribute information of the object selected for subsequent recognition and to define the subsequent search area around that created target model. Cavallaro teaches automatically determining a template from the detected object and its position (Cavallaro ¶ [0061]), generating templates “on the fly for each tracked object” (¶ [0080]), and defining the search area based on the template’s size and location (¶ [0111]). Doing so would predictably provide a target-specific model and corresponding search region for subsequent matching, thereby enabling accurate subsequent detection of the selected target.
Regarding Claim 5 (Currently Amended),
Tomotaka and Cavallaro teach the object detector according to claim 1.
Tomotaka and Cavallaro further teach: the second detector creates a template image based on the information on the outer shape of the target and performs a matching process by using the template image (Tomotaka further teaches that the second recognition unit selects “a template Tl corresponding to the target object 51 from the plurality of templates Tl in accordance with the type of the target object 51 recognized in the first recognition process” (Tomotaka ¶ [0042]), wherein the recognized object information includes “shape” (¶ [0019]).
Cavallaro further teaches that a template can “can conform to the shape of the object” and “can be determined automatically from the detected position of an object in an image” (¶ [0061]), and that templates “can be generated on the fly for each tracked object” (¶ [0080]).
Thus, Tomotaka in view of Cavallaro teaches the second detector creating a template image based on information on the outer shape of the target and performing the matching process using the template image.)
Regarding Claim 6 (Original),
Tomotaka and Cavallaro teach the object detector according to claim 1.
Tomotaka further discloses: wherein the second detector detects the target by performing the matching process in the search area of the image (Tomotaka teaches that the second recognition unit performs pattern matching by applying template T1 within a range including position of object 51, e.g., frame B1 (¶ [0043]).
Regarding Claim 8 (Original),
Tomotaka and Cavallaro teach the object detector according to claim 1.
Tomotaka further discloses: further comprising an interface connectable to or communicable with a robot controller that controls a robot (Tomotaka teaches a communication interface communicates with the robot control system (i.e. robot controller) (¶ [0069]), wherein the robot control system is configured to control a robot (¶¶ [0070]- [0071]).).
Regarding Claim 9 (Currently Amended),
Tomotaka and Cavallaro teach the object detector according to claim 1.
Tomotaka further teaches: A robot system (see Tomotaka ¶ [0001], “a robot system”) comprising: the object detector
a robot (Fig. 1, element 3; ¶ [0001]; ¶ [0073] “robot system further including the robot 3”);
and a robot controller that controls the robot such that the robot applies a treatment to the target detected by the object detector (¶ [0047]; ¶ [0073]).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to employ the object detector of Tomotaka, as modified by Cavallaro and as discussed with respect to claim 1, in Tomotaka’s robot system because Tomotaka teaches employing its recognition system to recognize an object for usage by the robot (Tomotaka ¶ [0047]; ¶ [0073]).
Regarding claim 10 (Currently Amended),
Tomotaka teaches: A non-transitory storage medium storing an object detection program that causes a computer to perform the functions (Tomotaka teaches “A recognition program according to an aspect is a program for causing one or more processors to execute the recognition method” (¶ [0064]), wherein the program may be “recorded and provided in a non-transitory recording medium such as a memory card, an optical disk, or a hard disk drive, which is readable by the computer system” and executed by a processor (¶ [0067]). Thus, Tomotaka teaches the claimed non-transitory storage medium storing a program that causes a computer to perform object detection.
The remaining object-detection functions recited in claim 10 correspond to the object-detection limitations of claim 1 and are taught or suggested by Tomotaka in view of Cavallaro for the reasons set forth above, in claim 1.
Claims 4 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Tomotaka (JP 2020107142 A; paragraph numbers correspond to machine translated copy provided by applicant in IDs, see corresponding Figs in original copy provided by applicant in the IDs), in view of Cavallaro (US 20090028385 A1), and in further view of Yang (US 20160210525 A1; provided in references cited of Non-final Office Action mailed on 04/03/2026).
Regarding claim 4 (Currently Amended),
Tomotaka and Cavallaro teach the object detector according to claim 1.
Tomotaka further discloses: wherein the selector extracts a representative portion of the target (Tomotaka teaches recognizing a plurality of types of articles 5 (also referred to throughout the disclosure as target objects) within image data and obtaining position coordinates of the recognized articles (¶ [0040]). Tomotaka further teaches that the first features of an object includes “the type, shape, size, and pattern of the target object 51, the color distribution in the target object 51” and “the position of the target object 51 in the image D1” (¶ [0019]). Tomotaka further teaches extracting feature points of an object from the image data and using the extracted feature points in determining the target object (¶¶ [0044]-[0047]; Figs. 3-4). The extracted feature points reasonably correspond to a representative portion of the target, as feature points represent portions/features of the detected object used in identifying the object as the target.
However, Tomotaka and Cavallaro fail to explicitly disclose extracting the representative portion of the target in three-dimensional information corresponding to the image.
In a related art, Yang teaches: In a related art, Yang teaches: applying its “object detection operations” in “three-dimensional (3D) scenarios,” wherein search-area points “may all be in 3D space and may have (x, y, z) coordinates” (¶ [0033]). Yang further teaches “using location data from a three-dimensional (3D) map” to “narrow a search area” during object detection (¶ [0050]), generating a “search area mask based on the 3D map” (¶ [0054]), and projecting “3D positions…onto an image plane” (¶ [0056]). Yang expressly teaches that “the processor 108 may determine a search area or areas based on 3D map data” and that “The object detector may perform object detection in the search area” (¶ [0058]). Also see ¶¶ [0060]-[0063]. Thus, Yang teaches using three-dimensional information corresponding to image data to in performing object detection operations on portions of the image associated with an object to be detected.
Tomotaka, Cavallaro, and Yang are analogous art because they’re directed to object detection and/or recognition using image information, while Tomotaka and Yang both aim to reduce object detection/recognition processing by limiting the area subjected to subsequent detection or recognition, and Yang further teaches using three-dimensional information to constrain the search area.
Tomotaka, Cavallaro, and Yang are analogous art because they’re all directed to object detection and/or recognition and each teaches techniques of limiting or defining an area in which subsequent object detection or recognition processing is performed in order to enable efficient object detection. Yang further teaches using three-dimensional information to limit the area in which the object detection operation is performed.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify the teachings of Tomotaka, as modified by Cavallaro, to use Yang’s three-dimensional information in performing the object detection and target selection operations, in order to reduce the are analyzed and thereby decrease object detection time, as Yang expressly teaches that use of 3D map data may enable “faster object detection and further reduction of scan area(s)” (Yang ¶ [0059]), consistent with Tomotaka’s objective of reducing object-recognition time (see Tomotaka p. 3 “Problem to be Solved” section).
Regarding Claim 7 (Original),
Tomotaka and Cavallaro teach the object detector according to claim 1.
Tomotaka further discloses: wherein the setter sets a (As discussed with respect to claim 1, Tomotaka teaches setting a limited search area corresponding to the detected object and subsequently performing pattern matching within the limited search area (See claim 1’s 103 rejection, and Tomotaka ¶¶ [0034]-[0035] and ¶¶ [0040]-[0047].)
However, Tomotaka in view of Cavallaro fail to explicitly disclose setting the search area using three-dimensional information or performing the object detection with respect to a three-dimensional search area.
In a related art, Yang teaches: applying its “object detection operations” in “three-dimensional (3D) scenarios,” wherein search-area points “may all be in 3D space and may have (x, y, z) coordinates” (¶ [0033]). Yang further teaches “using location data from a three-dimensional (3D) map” to “narrow a search area” during object detection (¶ [0050]), generating a “search area mask based on the 3D map” (¶ [0054]), and projecting “3D positions…onto an image plane” (¶ [0056]). Yang expressly teaches that “the processor 108 may determine a search area or areas based on 3D map data” and that “The object detector may perform object detection in the search area” (¶ [0058]). Also see ¶¶ [0060]-[0063]. Thus, Yang teaches using three-dimensional information corresponding to image data to establish a search area and performing object detection within the resulting search area.
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the object detector taught by Tomotaka, as modified by Cavallaro, to utilize Yang’s teachings of three-dimensional information in establishing the search are for detecting the target, in order to reduce the area searched and thereby decrease time required for object detection, as Yang expressly teaches that use of 3D map data may enable “faster object detection and further reduction of scan area(s)” (Yang ¶ [0059]), consistent with Tomotaka’s objective of reducing object-recognition time (see Tomotaka p. 3 “Problem to be Solved” section).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAMUEL DAVID BAYNES whose telephone number is (571)272-0607. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
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, Stephen R Koziol can be reached at (408)918-7630. 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.
/SDB/
Samuel D. Baynes
Examiner, Art Unit 2665
/Stephen R Koziol/Supervisory Patent Examiner, Art Unit 2665
Prosecution Insights