DETAILED ACTION
Claims 1-10 are pending in this application and have been examined under the priority date of 04/21/2021 in reference to the provisional application. Claims 1 and 3 have been amended in this application and claims 11-17 have been canceled.
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
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/02/2023 and 05/18/2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/28/2026 has been entered.
Response to Arguments
35 U.S.C. 101
Applicant’s arguments (see Remarks, filed 05/18/2026) have been fully considered by the examiner, given that claims 11-17 are canceled, the rejections made to the claims under 35 U.S.C. 101 are moot.
35 U.S.C. 103
Applicant’s arguments (see Remarks, filed 02/05/2026) have been fully considered by the examiner and are not persuasive. Applicant argues (see Remarks filed 02/05/2026) that neither Zhang nor Holzer teaches “making a comparison of the respective quality metric to a predetermined quality threshold” because Zhang does not teach a quality-based metric or a predetermined threshold. The examiner disagrees, and notes that in [0023] of the applicant’s specification, the quality metric is defined as a parameter of image quality such as sharpness, brightness, or contrast. Further, the broadest reasonable interpretation of this limitation is that any metric pertaining to image quality, which may be any visual quality pertinent to the analysis being performed, be compared to a predetermined value or limit. Zhang teaches in [0076] and [0096] that the images are selected based on preset screening conditions which can include image clarity and the clarity is compared to a threshold, which would be understood as a parameter of image quality by one of ordinary skill in the art.
The applicant further argues (see Remarks filed 02/05/2026) that this metric is not used to select a subset of images because the disclosure of Zhang teaches away from this. The examiner disagrees, Zhang paragraph [0076] teaches that images are categorized into “type” sets, then the sets have the images which have the highest determined clarity selected as a set. This step takes the overall set of images, and subsets the images into a set of images which have the highest quality, which is functionally equivalent to generating an image subset as understood by one of ordinary skill in the art.
PNG
media_image1.png
272
330
media_image1.png
Greyscale
(Zhang, [0076])
PNG
media_image2.png
50
328
media_image2.png
Greyscale
PNG
media_image3.png
120
334
media_image3.png
Greyscale
(Zhang, [0096])
The applicant further argues (see Remarks filed 02/05/2026) that Holzer fails to teach “wherein determining the respective quality metric further comprises, assigning an object access parameter that indicates a degree to which the first component is covered, the object access parameter varying based on time”. The examiner disagrees, Holzer teaches in [0071]- [0073] that multiple parameters are used to determine whether the images are suitable quality for analysis, further it teaches in [0204]-[0206] that one of these parameters is object coverage to determine whether or not the object is visible in the image or video frame. Further, Holzer teaches in paragraph [0262] that the images are analyzed over time using video data, indicating that the parameters assessed are time variant. One of ordinary skill in the art would understand that real time video analysis or analysis of the same object over the duration of a video would indicate that these assessed parameters may be time variant. For at the reasons discussed above, the examiner maintains the rejections made under 35 U.S.C. 103 over Zhang and in further view of Holzer.
PNG
media_image4.png
396
376
media_image4.png
Greyscale
(Holzer, [0071]- [0073])
PNG
media_image5.png
314
372
media_image5.png
Greyscale
(Holzer, [0204]- [0206])
PNG
media_image6.png
310
364
media_image6.png
Greyscale
(Holzer, [0262])
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.
1. Claims 1-10 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US 20200050867 A1) in view of Holzer (US 20200234488A1).
Regarding claim 1 Zhang discloses; A method comprising: capturing a plurality of images of a system,
the plurality of images defining different components of the system captured from a plurality of points of view (Zhang, [0039] the client obtains video data and the data is sent to the server, [0040] further clarifies that the server processes frames of images in the video data, therefore there are multiple images obtains in the video data, [0042] the video/image data is captures from multiple angles to show the same damaged portion of the vehicle body, indicating multiple points of view, [0044] the damaged portion of the vehicle (components) is identified and classified with its location and size);
training a computer system to perform operations comprising (Zhang, [0046] the system has a damage detection model which is trained):
based on the plurality of images, detecting a plurality of findings associated with at least one of the components (Zhang, [0043]-[0044] the server detects video images in captured video data to identify the damaged portion of the of the vehicle in the images, [0048] the network takes the image as input, the output of the network is a selection of multiple damaged regions and there confidences, where the confidence is a parameter indicating the degree of authenticity of the identified region.),
the findings each corresponding to an anomaly, or to a portion of a given image that is different than what is expected (Zhang, [0043]-[0044] the server detects video images in captured video data to identify the damaged portion of the vehicle in the images, where the damage is being interpreted as being analogous to an anomaly);
PNG
media_image7.png
54
324
media_image7.png
Greyscale
PNG
media_image8.png
134
332
media_image8.png
Greyscale
(Zhang, [0048])
PNG
media_image9.png
486
676
media_image9.png
Greyscale
(Zhang, Figure 1 showing the steps indicated, where the video is captured, components/damaged portions are identified and then classification is performed)
PNG
media_image10.png
512
530
media_image10.png
Greyscale
(Zhang, Figure 5, showing the components from the image as inputs, and the parameters (type of damage) as outputs)
determining a first component associated with each finding of the plurality of findings (Zhang, [0055] during analysis the video frames are analyzed to determine whether a vehicle component is damaged. [0056] a close-up image set including images displaying the damaged portion and a component image set including images displaying a vehicle component to which the damaged portion belongs, which is analogous to a first component for each finding, where the finding is the damage, [0057] the classifications including the damage type is included);
PNG
media_image11.png
656
394
media_image11.png
Greyscale
(Zhang, [0055]- [0057])
determining a respective quality associated with each of the images in the set of images (Zhang, [0061] the damage portions are determined as specific type based upon how large of an area the damage is over, this is compared using a threshold, [0096] the server detects whether or not the clarity of an image (quality metric) is sufficient using a threshold) or associated with each finding included in each image in the set of images,
wherein the respective quality metric is determined by parameters associated with each of the images of the respective finding included in each image (Zhang, [0076] images satisfying preset conditions are selected, where the images must meet a clarity requirement to be selected and the images must contain sections of a vehicle which have damage, the examiner is interpretating the clarity of the image as being the quality metric associated with an image parameter, and the damage of the vehicle in the image as being a finding included in the image, applicant defines in [0023] of the specification that the quality metric has to do with parameters of the images, such as sharpness (clarity), brightness, object display range or contrast, therefore the image clarity would be analogous to this);
making a comparison of the respective quality metric to a predetermined quality threshold (Zhang, [0076] images satisfying preset conditions are selected, where the images must meet a clarity requirement to be selected and the images must contain sections of a vehicle which have damage, the examiner is interpretating the clarity of the image as being the quality metric associated with an image parameter, and the damage of the vehicle in the image as being a finding included in the image, [0096] the server detects whether or not the clarity of an image (quality metric) is sufficient using a threshold comparison);
and based on the comparison, selecting a subset of images of the plurality of images that meet or exceed the predetermined quality threshold for display to an operator associated with the system (Zhang, [0075] states the server uses a vehicle loss assessment image to classify the images based on a present condition, [00139] where the region where the damage occurs is displayed and identified through detection of the region in the video images, [00083] the served send the region of the damaged portion to the client to display in real time, where the damage portion may be identified and displayed, and the use of an operate may facilitate observation, [0076] images must meet a clarity threshold (quality threshold) to be selected),
[wherein determining the respective quality metric further comprises, assigning an object access parameter that indicates a degree to which the first component is covered,
the object access parameter varying based on time.]
Zhang fails to teach; wherein determining the respective quality metric further comprises, assigning an object access parameter that indicates a degree to which the first component is covered,
the object access parameter varying based on time.
However, in the same field of endeavor, Holzer teaches;
wherein determining the respective quality metric further comprises, assigning an object access parameter that indicates a degree to which the first component is covered (Holzer, [0154] the damage detection operation may be used to identify an object or component in an image, [0071]-[0073] the system determines whether the images suitable to detect object damage, and then multiple methods and parameters are used to determine the damage (quality parameters), [0204]-[0206] the object is mapped on a grid and then a determination can be made of whether the region is covered or in view (object access parameter), [0210] the system determines using an evaluation, a degree of coverage, which helps determine if a specific grid portion is covered or shown in the image),
the object access parameter varying based on time (Holzer, [0213] the uncertainty parameters, which are determined with regard to object coverage ([0210]- [0212]) may be determined for a set of frames, where [0262] the images/frames may be captured at different times, indicating the parameters/characteristics change over time).
The combination of Zhang and Holzer would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that when detecting defects or other regions of interest in an image, the ability to verify that regions or components of interest are visible or not visible in the image would allow for accurate assessment, as well as for the user to determine if more images are required. (Holzer, [0200]- [0215] and [0234])
Regarding claim 2 the combination of Zhang and Holzer teaches; The method as recited in claim 1, wherein determining the respective quality metric further comprises:
assigning a value related to each of a plurality of quality parameters (Zhang, [0061] the damage portions are determined as specific type based upon how large of an area the damage is over, this is compared using a threshold, where the size, width or area of the damage is compared to a threshold to determine the type of damage, further [0062]-[0068] discusses multiple value based metrics which can be assigned to each damage type including a ratio of the area of the damage, or a value corresponding to the pixels in the damaged region or span of the damage),
each quality parameter representative of a feature of the images that can be distinguished by a human eye (Zhang, [0061]- [0068] the regions of damage are visible in the images and being classified based on size and pixel number, where each damaged regions (features) being assessed using parameters are visible to a human).
Regarding claim 3 the combination of Zhang and Holzer teaches; The method as recited in claim 2, wherein the plurality of quality parameters define the object access parameter (Holzer, [0154] the damage detection operation may be used to identify an object or component in an image, [0071]-[0073] the system determines whether the images suitable to detect object damage, and then multiple methods and parameters are used to determine the damage (quality paraments), [0204]-[0206] the object is mapped on a grid and then a determination can be made of whether the region is covered or in view (object access parameter)),
the object access parameter indicating that the first finding is blocked in the respective image from view by the human eye (Holzer, [0210] the system determines using an evaluation of a degree of coverage, which helps determine if a specific grid portion is covered or shown in the image, [0204]-[0206] and figure 8, the system determines how much of the object is covered or if the object is sufficiently covered, [0234] points can be determined as visible or invisible from the human eye using the coverage analysis.).
The combination of Zhang and Holzer would have been obvious to one of ordinary skill in the art prior to the effective filing date of the presently claimed invention. The motivation for the combination lies in that when detecting defects or other regions of interest in an image, the ability to verify that regions or components of interest are visible or not visible in the image would allow for accurate assessment, as well as for the user to determine if more images are required. (Holzer, [0200]- [0215] and [0234])
Regarding claim 4 the combination of Zhang and Holzer teaches; The method as recited in claim 3, wherein determining the quality metrics further comprises:
determining a weight associated with each of the plurality of quality parameters (Zhang, [0048] during training the parameters of the network are determined using the training images which have been marked, where mini batching is a method that uses weighting to determine model parameters based on training data. [0049] the parameters of the model are used to determine the damaged regions and the degree of certainty that the region is damaged), wherein the weight is based on the first component (Zhang, [0048] during training the parameters of the network are determined using the training images which have been marked, where mini batching is a method that uses weighting to determine model parameters based on training data. [0049] the parameters of the model are used to determine the damaged regions (components) and the degree of certainty that the region is damaged);
and aggregating the plurality of quality parameters in accordance with their respective weights (Zhang, [0049] the parameters of the model (determined based on the data indicating the components) are determined using a mini batch method where they are weighted, further [0048] the model is trained using the quality data, and the training process includes a step of aggregation and parameter determination, as well as weighting using the mini-batch step), so as to compute the quality metrics (Zhang, [0049] the parameters of the model (determined based on the data indicating the components) are determined using a mini batch method where they are weighted, further [0048] the model is trained using the quality data, and the training process includes a step of aggregation and parameter determination, as well as weighting using the mini-batch step).
Regarding claim 5 the combination of Zhang and Holzer teaches; The method as recited in claim 4, wherein the weight is further based on context information associated with the images, the context information indicating an environment of the first component when the images are captured (Zhang, [0048] the parameters of the model are determined using a mini-batch step which weights them, this is done during training which uses the image data including the components, where [0045] the region/location of the damaged portion (environment of the component/context information) are identified by the network as well when determining the parameters).
Regarding claim 6 the combination of Zhang and Holzer teaches; The method(Zhang, [0048] the parameters of the model are determined using a mini-batch step which weights them, this is done during training which uses the image data including the components, where [0045] the region/location of the damaged portion (environment of the component/context information) are identified by the network as well when determining the parameters, the model parameters generated, [0046] the network damage detection model is training using the above methods to be used for damage detection (quality metrics), therefore the determination of these metrics by the model would also be based on the weights and parameters generated during training).
Regarding claim 7 the combination of Zhang and Holzer teaches; The method as recited in claim 1, the method further comprising: based on the respective quality metric, ranking each image in the subset of images so as to define a first image having the highest quality metric (Zhang, [0090] multiple images which have the highest clarity are selected to be used for damage assessment);
and displaying the first image having the highest quality metric (Zhang, [0090] multiple images which have the highest clarity are selected to be used for damage assessment, where the images selected to the display (first images) hive the best quality of the batch).
Regarding claim 8 the combination of Zhang and Holzer teaches; The method as recited in claim 7, the method further comprising: identifying a point of view associated with each image in the subset of images (Zhang, [0078] the angle of the photographer (angle of the image capture) can be determined), the point of view defined by a direction from which the first component is viewable in the respective image (Zhang, [0078] the angle of the photographer (angle of the image capture) can be determined, [0081] the angle of view and location of filming/image capture may change, and this may be determined by the server), so as define multiple point of view classifications (Zhang, [0041] multiple videos are captured of the same component from multiple angles to obtain multiple points of view);
and based on the respective quality metric, ranking each image in the subset of images with respect to each of the multiple point of view classifications (Zhang, [0090] multiple images which have the highest clarity and multiple filming angles are selected to be used for damage assessment, where the images selected to the display (first images) hive the best quality of the batch).
Regarding claim 9 the combination of Zhang and Holzer teaches; The method as recited in claim 8, wherein the first image is associated with a first point of view classification, the method comprising:
responsive to a user actuation, selecting a second image from a second point of view classification that is different than the first point of view classification (Zhang, [0051] location regions in the image may be selected, [0057] multiple image frames may be selected and processed, [0076] multiple images may be selected for having good clarity and multiple angles);
and displaying the second image instead of the first image (Zhang, [0076] a combination of one or more images may be displayed, [0084] in processing a damaged region from an image may be displayed, further the client may select a new damaged region, and send that information to the server for processing, since all damaged portions from photographs as displayed at different points in the processing, it would be inherent that when a user selects a new photograph, this would be displayed at a later time in place of the first image. ).
Regarding claim 10 the combination of Zhang and Holzer teaches; The method as recited in claim 9, the method further comprising:
based on the respective quality metric, determining that the second image has a higher rank as compared to the other images associated with the second point of view classification (Zhang, [0010] the plurality video image frames are classified and a ratio or value is generated for each, [0011] the images are then ordered in descending order (highest rank first) based on this classification, therefore there is inherently a step of determining which images in the set have the higher rank or score or classification).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Prior art made of record but not relied by the examiner can be found on the attached PTO-892 Notice of References Cited form.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JORDAN M ELLIOTT whose telephone number is (703)756-5463. The examiner can normally be reached M-F 8AM-5PM ET.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/J.M.E./Examiner, Art Unit 2666 /EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666
Prosecution Insights