DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Applicant’s response to the Non-final Office Action dated 10/10/2025, filed with the office on 01/12/2026, has been entered and made of record.
Response to Amendment
In light of Applicant’s amendment of claim 4, the rejection of record of claim 4 under 35 U.S.C. 112(b) has been withdrawn.
Status of Claims
Claims 1-20 are pending. Claims 1, 4-8, 11, 12, 14, 17 and 20 are amended.
Response to Arguments
Applicant’s amendment of independent Claims 1, 11 and 17, which has altered the scope of the claims of the instant application, has necessitated the new ground(s) of rejection presented in this office action with respect to claims of the instant application. Accordingly, in response to Applicant’s arguments that are merely directed to the amended portion of the claims, new analyses have been presented below, which make Applicant’s arguments moot.
Consequently, THIS ACTION IS MADE FINAL.
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-6, 9-13 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Tang et al. (US 2021/0350516 A1) in view of Shen et al. (US 2017/0294010 A1) and still in further view of Kamal et al. (US 2020/0273147 A1).
Regarding claim 1, Tang teaches, A system comprising: a non-transitory memory; and one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory (Tang, ¶0020: “a computer system to perform the set of operations… hardware module may constitute general-purpose hardware as well as a non-transitory computer-readable medium that stores program instructions”) to cause the system to perform operations comprising: accessing a first image of a document for a user that is submitted (Tang, ¶0030: “System 100 may utilize image processing module 110 to automatically extract information from images uploaded by these customers to system”) for a document verification process of the document; (Tang, ¶0002: “users to upload documents for identification and verification purposes”) executing an image processing neural network (NN) framework comprising at least a first NN (Tang, ¶0061: “computing system analyzes, using a first neural network, the image to identify at least one document object”) and a second NN, (Tang, ¶0062: “a second neural network”) wherein the first NN is associated with an object detection operation for the document verification process, (Tang, ¶0061: “the first neural network is a binary classification that indicates whether or not the one or more objects included in the image are document objects”) and wherein the second NN is associated with an object classification operation for the document verification process; (Tang, ¶0062: “computing system determines, using a second neural network, whether the document object within the image corresponds to a particular one of the document types specified in the set of known document types”) identifying, using the first NN, a plurality of key information fields (KIFs) of the document in the first image for the object detection operation; (Tang, ¶0044: “Document detection module 120, in the illustrated embodiment, receives image 102 and generates, using single-pass neural network 360, bounding boxes 352 for one or more document objects included in image”) , (Tang, ¶0026: “whether the quality of the image is too poor for the system to perform data extraction. Such poor-quality images may be rejected by the disclosed system”) and requesting, from the user for the document verification process, one of a second image of the document or the corresponding document data for the one of the plurality of KIFs. (Tang, ¶0067: “computing system may reject the document and/or request that a user upload a new image of the document”). However, Tang does not explicitly teach, evaluating, using the second NN, a quality of each of the plurality of KIFs in the first image for the object classification operation, wherein evaluating includes determining a score for the quality of each of the plurality of KIFs; identifying, using the second NN based on the evaluating, an image area within the first image corresponding to one of the plurality of KIFs that is below or at a threshold image quality for extraction of corresponding document data for the document, wherein the image area comprises a portion of the first image that includes image data having the corresponding document data; calculating an overall document quality score of the first image containing the document based on the score for the quality of each of the plurality of KIFs and a document type of the document.
In an analogous field of endeavor, Shen teaches, evaluating, using the second NN, a quality of each of the plurality of KIFs in the first image for the object classification operation, (Shen, ¶0036: “identifying attributes that are present in a digital image… neural network to generate an attribute quality score for individual attributes”) wherein evaluating includes determining a score for the quality of each of the plurality of KIFs; (Shen, ¶0036: “generate an attribute quality score for individual attributes”) identifying, using the second NN based on the evaluating, an image area within the first image (Shen, ¶0039: “An architecture of the regression CNN 102 can include a stack of distinct layers that process portions of an input image”) calculating an overall document quality score (Shen, ¶0084: “an aesthetic quality score can include both an overall quality score in addition to one or more specific attribute quality scores”) of the first image containing the document based on the score for the quality of each of the plurality of KIFs (Shen, ¶0034: “neural network can further provide an aesthetic quality score that includes an identification of one or more attributes detected within a digital image”) and a document type of the document; (Shen, ¶0033: “neural network to consider the type of content of a digital image when determining an aesthetic quality score”).
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 Tang using the teachings of Shen to introduce an evaluating quality scores for documents. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of rejecting documents with poor quality data. Therefore, it would have been obvious to combine the analogous arts Tang and Shen to obtain the above-described limitations in claim 1. However, the combination of Tang and Shen does not explicitly teach, an image area within the first corresponding to one of the plurality of KIFs that is below or at a threshold image quality for extraction of corresponding document data for the document, wherein the image area comprises a portion of the first image that includes image data having the corresponding document data.
In another analogous field of endeavor, Kamal teaches, an image area within the first corresponding to one of the plurality of KIFs that is below or at a threshold image quality for extraction of corresponding document data for the document, (Kamal, ¶0044: “autonomously determine that each image segment of the image segment set used by stitching system 101 in the failed attempt to generate the panoramic image satisfies a predetermined image quality threshold”) wherein the image area comprises a portion of the first image that includes image data having the corresponding document data (Kamal, ¶0055: “first portion depicted in image segment 502-T3), 408-12, and 408-13, and a second portion of shape object 408-14 (e.g., a portion that is different from but complementary to the first portion depicted in image segment 502-T1”).
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 Tang in view of Shen using the teachings of Kamal to introduce quality assessment of image portion. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of rejecting documents based on poor quality in a portion of image data. Therefore, it would have been obvious to combine the analogous arts Tang, Shen and Kamal to obtain the invention in claim 1.
Regarding claim 2, Tang in view of Shen and in further view of Kamal teaches, The system of claim 1, wherein, prior to the accessing, the operations further comprise: accessing the first NN for the object detection operation trained using training data associated with a plurality of training documents; (Tang, ¶0033: “a training set 252 for training a single-pass neural network (e.g., a you-only-look-once (YOLO) neural network, a single shot multibox detector”) and accessing the second NN for the object classification operation trained based on image data in each of the plurality of KIFs from the plurality of training documents. (Tang, ¶0051: “residual neural network 460 may be trained to recognized documents that match known document types. For example, residual neural network 460 may predict document types 432 for documents included in image 102 based on attributes of those documents”).
Regarding claim 3, Tang in view of Shen and in further view of Kamal teaches, The system of claim 2, wherein the training data comprises training images of the plurality of training documents having labels for the plurality of KIFs in each of the plurality of training documents (Tang, ¶0070: “the training set may include an image of a driver's license and the label for this image specifies that it is a driver's license issued from the state of Texas”) and corresponding document types for the plurality of training documents, (Tang, ¶0070: “the training set includes various machine learning input features (e.g., images) with known labels (e.g., document types”) and wherein the second NN is further trained using the training images to predict the quality of the image data in the plurality of KIFs. (Shen, ¶0036: “identifying attributes that are present in a digital image, one or more embodiments of the image rating system can train the neural network to generate an attribute quality score for individual attributes”).
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 Tang in view of Shen and in further view of Kamal using the additional teachings of Shen to introduce training a quality score generating neural network. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the accuracy of the neural network. Therefore, it would have been obvious to combine the analogous arts Tang, Shen and Kamal to obtain the invention in claim 3.
Regarding claim 4, Tang in view of Shen and in further view of Kamal teaches, The system of claim 2, wherein the first NN was further trained using training data associated with document type predictions. (Tang, ¶0011: “training and using a residual neural network to determine a document type”).
Regarding claim 5, Tang in view of Shen and in further view of Kamal teaches, The system of claim 2, wherein the second NN was further trained for confidence level predictions that the image data includes the corresponding document data in the plurality of KIFs, (Tang, ¶0041: “The confidence score may specify the residual neural network's confidence that the predicted document type is a correct type”) and wherein the second NN comprises one of a Residual NN (ResNet) or an image assessment NN. (Tang, ¶0062: “the second neural network is a residual neural network (ResNet)”).
Regarding claim 6, Tang in view of Shen and in further view of Kamal teaches, The system of claim 1, wherein the action comprises generating a request for the user to resubmit the document through the second image. (Tang, ¶0067: “computing system may reject the document and/or request that a user upload a new image of the document”).
Regarding claim 9, Tang in view of Shen and in further view of Kamal teaches, The system of claim 1, wherein the action comprises an approval of the first image for a submission of the document for the document verification process, (Tang, ¶0029: “documents that are accepted by system 100 for identification and onboarding purposes”) and wherein the operations further comprise: performing the submission to the document verification process of the first image. (Tang, ¶0024: “Once the system has extracted identifying information from the document, the system may verify the identity of the user and onboard the user”).
Regarding claim 10, Tang in view of Shen and in further view of Kamal teaches, The system of claim 1, wherein the identifying, using the first NN, and the evaluating, using the second NN, are based on the document type of the document, (Tang, ¶0075: “computing system extracts information from the document object based the document type corresponding to a particular known type of document”) and wherein the first NN is configured to determine the document type in correspondence with the identifying. (Tang, ¶0023: “determining document types for documents included in an image… neural network may identify that the image uploaded by the user contains a United States driver's license”).
Regarding claim 11, Tang teaches, A method comprising: receiving a first image of a document (Tang, ¶0058: “a method for determining a document type for a document object included in an image”) requested to be verified by a service provider; (Tang, ¶0002: “users to upload documents for identification and verification purposes”) detecting, using a first neural network (NN) of an image processing NN pipeline, (Tang, ¶0061: “computing system analyzes, using a first neural network, the image to identify at least one document object”) a plurality of key information fields (KIFs) of the document that are present in the first image, (Tang, ¶0044: “receives image 102 and generates, using single-pass neural network 360, bounding boxes 352 for one or more document objects included in image”) wherein the first NN is configured to perform object detections in processed images, (Tang, ¶0026: “preprocessing on an image to attempt to remove a glare or to improve the clarity, or both of the image”) and wherein each of the plurality of KIFs include a portion of image data from the first image; (Tang, ¶0037: “perform object detection in two stages by first selecting interesting portions of an image and then classifying objects within those regions”) second NN is configured to perform object classifications (Tang, ¶0040: “neural network may indicate document object classifications and location information for objects included in images”) in the processed images; (Tang, ¶0026: “preprocessing on an image to attempt to remove a glare or to improve the clarity, or both of the image”) ; (Tang, ¶0026: “whether the quality of the image is too poor for the system to perform data extraction. Such poor-quality images may be rejected by the disclosed system”) and requesting one of a second image of the document or the corresponding document data for the one of the plurality of KIFs. (Tang, ¶0067: “computing system may reject the document and/or request that a user upload a new image of the document”). However, Tang does not explicitly teach, scoring, using a second NN of the image processing NN pipeline, the portion of the image data in each of the plurality of KIFs and identifying, using the second NN based on the scoring, an image area within the first image corresponding to one of the plurality of KIFs that is below or at a threshold image quality for extraction of corresponding document data for the document, wherein the image area comprises a portion of the image data having the corresponding document data; calculating an overall document quality score of the first image containing the document based on the scored portions of the image data and a document type of the document.
In an analogous field of endeavor, Shen teaches, scoring, using a second NN of the image processing NN pipeline, the portion of the image data in each of the plurality of KIFs, (Shen, ¶0036: “identifying attributes that are present in a digital image… neural network to generate an attribute quality score for individual attributes”) and identifying, using the second NN based on the scoring, an image area within the first image (Shen, ¶0039: “An architecture of the regression CNN 102 can include a stack of distinct layers that process portions of an input image”) calculating an overall document quality score (Shen, ¶0084: “an aesthetic quality score can include both an overall quality score in addition to one or more specific attribute quality scores”) of the first image containing the document based on the scored portions of the image data (Shen, ¶0034: “neural network can further provide an aesthetic quality score that includes an identification of one or more attributes detected within a digital image”) and a document type of the document; (Shen, ¶0033: “neural network to consider the type of content of a digital image when determining an aesthetic quality score”).
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 Tang using the teachings of Shen to introduce an evaluating quality scores for documents. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of rejecting documents with poor quality data. Therefore, it would have been obvious to combine the analogous arts Tang and Shen to obtain the above-described limitations in claim 11. However, the combination of Tang and Shen does not explicitly teach, an image area within the first image corresponding to one of the plurality of KIFs that is below or at a threshold image quality for extraction of corresponding document data for the document, wherein the image area comprises a portion of the image data having the corresponding document data.
In another analogous field of endeavor, Kalam teaches, an image area within the first image corresponding to one of the plurality of KIFs that is below or at a threshold image quality for extraction of corresponding document data for the document, (Kamal, ¶0044: “autonomously determine that each image segment of the image segment set used by stitching system 101 in the failed attempt to generate the panoramic image satisfies a predetermined image quality threshold”) wherein the image area comprises a portion of the image data having the corresponding document data; (Kamal, ¶0055: “first portion depicted in image segment 502-T3), 408-12, and 408-13, and a second portion of shape object 408-14 (e.g., a portion that is different from but complementary to the first portion depicted in image segment 502-T1”).
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 Tang in view of Shen using the teachings of Kamal to introduce quality assessment of image portion. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of rejecting documents based on poor quality in a portion of image data. Therefore, it would have been obvious to combine the analogous arts Tang, Shen and Kamal to obtain the invention in claim 11.
Regarding claim 12, Tang in view of Shen and in further view of Kamal teaches, The method of claim 11, wherein the document is determined to be incapable of being verified in the first image, (Tang, ¶0026: “the system determines that the image is unusable, the system may reject the image”) and wherein the method further comprises: requesting a capture of the second image of the document. (Tang, ¶0067: “computing system may reject the document and/or request that a user upload a new image of the document”).
Regarding claim 13, Tang in view of Shen and in further view of Kamal teaches, The method of claim 12, wherein prior to the requesting, the method further comprises: determining that the portion of the image data in a corresponding at least one of the plurality of KIFs is incapable of being read or repaired in the first image. (Tang, ¶0067: “neural network being unable to identify a document object… then the computing system may reject the document and/or request that a user upload a new image of the document”).
Regarding claim 16, Tang in view of Shen and in further view of Kamal teaches, The method of claim 11, wherein the calculating the overall document quality score includes weighting each of the scored portions of the image data (Shen, ¶0076: “regression CNN weights different attributes more heavily when generating an aesthetic quality score for a digital image that contains one or more corresponding attributes”) based on the document type of the document. (Tang, ¶0064: “one or more weights are generated based on the confidence scores for the determined document types and whether the determined document types match known document types”).
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 Tang in view of Shen and in further view of Kamal using the additional teachings of Shen to introduce weighting image portions. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the scoring of the overall document quality based on the importance of individual attribute. Therefore, it would have been obvious to combine the analogous arts Tang, Shen and Kalam to obtain the invention in claim 16.
Claims 7-8 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Tang et al. (US 2021/0350516 A1), in view of Shen et al. (US 2017/0294010 A1), in further view of Kamal et al. (US 2020/0273147 A1) and still in further view of Staar et al. (US 2020/0279107 A1).
Regarding claim 7, Tang in view of Shen and in further view of Kamal teaches, The system of claim 1, wherein the operations further comprise: identifying the one of the plurality of KIFs to the user during the requesting.
In an analogous field of endeavor, Staar teaches, identifying the one of the plurality of KIFs to the user during the requesting. (Staar, ¶0036: “low-quality segments may be displayed on a graphical user interface according to a color scheme to help the user identify probably faulty segments”).
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 Tang in view of Shen and in further view of Kamal using the teachings of Staar to introduce identifying low-quality segments. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the quality of the image. Therefore, it would have been obvious to combine the analogous arts Tang, Shen, Kamal and Staar to obtain the invention in claim 7.
Regarding claim 8, Tang in view of Shen, in further view of Kamal and still in further view of Staar teaches, The system of claim 7, wherein the identifying the one of the plurality of KIFs further comprises providing an instruction for the user that includes information for capturing the second image having a higher quality of at least the image area corresponding the one of the plurality of KIFs. (Staar, ¶0034: “select or discard image segments depending on their respective values of the quality indicator, or decide whether a portion of the digital image should be rescanned, e.g. at a higher resolution”).
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 Tang in view of Shen, in further view of Kamal and still in further view of Staar using the additional teachings of Staar to introduce capturing a higher resolution image. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving image quality. Therefore, it would have been obvious to combine the analogous arts Tang, Shen, Kamal and Staar to obtain the invention in claim 8.
Regarding claim 14, Tang in view of Shen and in further view of Kamal teaches, The method of claim 12, further comprising: identifying an error in the first image that causes the document to be incapable of being verified in the first image; (Tang, ¶0022: “image may be rejected if the information depicted in an image of the document is illegible (e.g., if the image is blurry”). However, the combination of Tang, Shen and Kamal does not explicitly teach, outputting the error with the requesting of the capture.
In an analogous field of endeavor, Staar teaches, outputting the error with the requesting of the capture. (Staar, ¶0036: “low-quality segments may be displayed on a graphical user interface according to a color scheme to help the user identify probably faulty segments”; the output is interpreted as a display; see Applicant’s specification ¶0069: “output component, such as a display 511”).
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 Tang in view of Shen and in further view of Kamal using the teachings of Staar to introduce identifying errors within the image. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the quality of the image by resolving the errors. Therefore, it would have been obvious to combine the analogous arts Tang, Shen, Kamal and Staar to obtain the invention in claim 14.
Claims 15, 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Tang et al. (US 2021/0350516 A1) in view of Shen et al. (US 2017/0294010 A1), in further view of Kamal et al. (US 2020/0273147 A1) and still in further view of Wang et al. (US 2022/0051375 A1).
Regarding claim 15, Tang in view of Shen and in further view of Kamal teaches, The method of claim 11, wherein the document is determined to be incapable of being verified in the first image, and wherein the method further comprises. However, the combination of Tang, Shen and Kamal does not explicitly teach, performing an image data repair of the portion of the image data in a corresponding at least one of the plurality of KIFs.
In an analogous field of endeavor, Wang teaches, performing an image data repair of the portion of the image data in a corresponding at least one of the plurality of KIFs. (Wang, ¶0034: “parameter models are used to recover different feature attributes of the image”).
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 Tang in view of Shen and in further view of Kamal using the teachings of Wang to introduce repairing image portions. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the quality of the image. Therefore, it would have been obvious to combine the analogous arts Tang, Shen, Kamal and Wang to obtain the invention in claim 15.
Regarding claim 17, Tang teaches, A non-transitory machine-readable medium having stored thereon machine-readable instructions (Tang, ¶0020: “a non-transitory computer-readable medium that stores program instruction”) executable to cause a machine to perform operations comprising: (Tang, ¶0020: “instructions that are executable by a computer system to perform the set of operations”) receiving a first image of a document for a document verification process of the document with a service provider; (Tang, ¶0002: “users to upload documents for identification and verification purposes”) detecting, using a first neural network (NN), a plurality of fields for key information in the document in the first image; (Tang, ¶0044: “receives image 102 and generates, using single-pass neural network 360, bounding boxes 352 for one or more document objects included in image”) (Tang, ¶0026: “whether the quality of the image is too poor for the system to perform data extraction”) whether to request a resubmission of the document, (Tang, ¶0067: “request that a user upload a new image of the document”) a second image of the document to the document verification process; (Tang, ¶0048: “classification values that meet (are equal to or greater than) this threshold value are then used”) and requesting one of the second image of the document or the corresponding document data for the one of the plurality of KIFs. (Tang, ¶0067: “computing system may reject the document and/or request that a user upload a new image of the document”). However, Tang does not explicitly teach, scoring, using a second NN, a plurality of first qualities of image data present in the plurality of fields; identifying, using the second NN based on the scoring, an image area within the first image corresponding to one of the plurality of fields that is below or at a threshold image quality for extraction of corresponding document data for the document, wherein the image area comprises a portion of the first image that includes the image data having the corresponding document data; determining a second quality of the image of the document based on the scored plurality of first qualities of the plurality of fields and a document type of the document; and perform a repair of the image data in one or more of the plurality of fields.
In an analogous field of endeavor, Shen teaches, scoring, using a second NN, a plurality of first qualities of image data present in the plurality of fields; (Shen, ¶0036: “identifying attributes that are present in a digital image… neural network to generate an attribute quality score for individual attributes”) identifying, using the second NN based on the scoring, an image area within the first image determining a second quality of the image of the document based on the scored plurality of first qualities of the plurality of fields (Shen, ¶0034: “neural network can further provide an aesthetic quality score that includes an identification of one or more attributes detected within a digital image”) and a document type of the document; (Shen, ¶0033: “neural network to consider the type of content of a digital image when determining an aesthetic quality score”).
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 Tang using the teachings of Shen to introduce an evaluating quality scores for documents. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of rejecting documents with poor quality data. Therefore, it would have been obvious to combine the analogous arts Tang, Shen and Kamal to obtain the above-described limitations in claim 17. However, the combination of Tang and Shen does not explicitly teach, an image area within the first image corresponding to one of the plurality of fields that is below or at a threshold image quality for extraction of corresponding document data for the document, wherein the image area comprises a portion of the first image that includes the image data having the corresponding document data; and perform a repair of the image data in one or more of the plurality of fields.
In another analogous field of endeavor, Kalam teaches, an image area within the first image corresponding to one of the plurality of fields that is below or at a threshold image quality for extraction of corresponding document data for the document, (Kamal, ¶0044: “autonomously determine that each image segment of the image segment set used by stitching system 101 in the failed attempt to generate the panoramic image satisfies a predetermined image quality threshold”) wherein the image area comprises a portion of the first image that includes the image data having the corresponding document data; (Kamal, ¶0055: “first portion depicted in image segment 502-T3), 408-12, and 408-13, and a second portion of shape object 408-14 (e.g., a portion that is different from but complementary to the first portion depicted in image segment 502-T1”).
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 Tang in view of Shen using the teachings of Kamal to introduce quality assessment of image portion. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of rejecting documents based on poor quality in a portion of image data. Therefore, it would have been obvious to combine the analogous arts Tang, Shen and Kamal to obtain the above-described limitations in claim 11. However, the combination of Tang, Shen and Kamal does not explicitly teach, perform a repair of the image data in one or more of the plurality of fields.
In still another analogous field of endeavor, Wang teaches, perform a repair of the image data in one or more of the plurality of fields. (Wang, ¶0034: “parameter models are used to recover different feature attributes of the image”).
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 Tang in view of Shen and in further view of Kamal using the teachings of Wang to introduce repairing image portions. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the quality of the image. Therefore, it would have been obvious to combine the analogous arts Tang, Shen, Kamal and Wang to obtain the invention in claim 17.
Regarding claim 18, Tang in view of Shen, in further view of Kamal and still in further view of Wang teaches, The non-transitory machine-readable medium of claim 17, wherein the first NN comprises an object detection NN modified by a key information field (KIF) extraction with a document classification. (Tang, ¶0061: “the first neural network is a binary classification that indicates whether or not the one or more objects included in the image are document objects”; ¶0023: “determining document types for documents … a United States driver's license”).
Regarding claim 19, Tang in view of Shen, in further view of Kamal and still in further view of Wang teaches, The non-transitory machine-readable medium of claim 17, wherein the second NN comprises a quality assessment NN corresponding to one of an artificial NN or an image assessment NN. (Tang, ¶0062: “the second neural network is a residual neural network (ResNet)”).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Tang et al. (US 2021/0350516 A1) in view of Shen et al. (US 2017/0294010 A1), in further view of Kamal et al. (US 2020/0273147 A1), still in further view of Wang et al. (US 2022/0051375 A1) and yet in further view of Staar et al. (US 2020/0279107 A1).
Regarding claim 20, Tang in view of Shen, in further view of Kamal and still in further view of Wang teaches, The non-transitory machine-readable medium of claim 17, wherein the resubmission is requested (Tang, ¶0067: “computing system may reject the document and/or request that a user upload a new image of the document”). However, the combination of Tang, Shen, Kalam and Wang does not explicitly teach, with an identification of at least one of the plurality of fields having an insufficient quality of the image data present based on a corresponding one of the plurality of first qualities.
In an analogous field of endeavor, Staar teaches, with an identification of at least one of the plurality of fields having an insufficient quality of the image data present based on a corresponding one of the plurality of first qualities. (Staar, ¶0036: “low-quality segments may be displayed on a graphical user interface according to a color scheme to help the user identify probably faulty segments”).
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 Tang in view of Shen in further view of Kamal and still in further view of Wang using the teachings of Staar to introduce identifying low-quality segments. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of improving the quality of the image. Therefore, it would have been obvious to combine the analogous arts Tang, Shen, Kalam, Wang and Staar to obtain the invention in claim 20.
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 MEHRAZUL ISLAM whose telephone number is (571)270-0489. The examiner can normally be reached Monday-Friday: 8am-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, Saini Amandeep can be reached on (571) 272-3382. 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.
/MEHRAZUL ISLAM/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662