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 .
DETAILED ACTION
1. The following Office action is in response to communications filed on 1/21/2025. Claims 21-40 are currently pending within this application.
Information Disclosure Statement
2. The information disclosure statement(s) filed on 2/13/2025 is/are in compliance with the provisions of 37 CFR 1.97, and has/have been considered and a copy/copies is/are enclosed with this Office action.
Claim Rejections – 35 USC § 102
3. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
4. Claims 21, 23, 27-28, 30, 34-35, 37, and 40 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Dura (US PGPub 2018/0285639) [hereafter Dura].
5. As to claim 21, Dura discloses a computer-implemented method (as shown in Figure 5), comprising determining, for a template image (reference image M1 shown in Figures 4 and 6-7) defining a layout of handwriting content (content of regions of interest Zr) for an image set, template area coordinates (points of interest associated with each region defined by four corners of the regions) defining bounding boxes dividing the template image into template areas; transforming the template area coordinates (using transformations T shown in Figures 6-7) to align with dimensions of an input digital image (acquired structured document image A1) within the image set; and determining a location of a handwriting content field (regions Za) within the input digital image by extracting, from the input digital image, landmark coordinates (coordinates of regions Za) indicating locations of handwriting content based on transforming the template area coordinates (Paragraphs 0042-0049, 0062-0070, 0074-0098, a device for analysis of a structured document, shown in Figure 2, includes a processor and memory that execute an operational method, shown in Figure 5, wherein a stored reference/template image defines a layout of content fields where handwriting is present within a specific type of document has the coordinates of the four corners of said fields extracted in order to generate a geometric transformation that characterizes distortions present within the input structured document images including the fields of interest present within the template image such that locations of relevant content fields within the input structured document images to be analyzed are determined through projection of the corresponding reference regions of the reference image onto the input structured document image after application of the determined transformation to the reference image).
6. As to claim 23, Dura discloses transforming the template area coordinates to align with the dimensions of the input digital image comprises extracting a first image region (Zr1-Zr4) from the template image and a second image region (Za1-Za4) from the input digital image; determining, utilizing a keypoint detection model (algorithm performed by image processing module 4), a first set of keypoints (corner coordinates and/or points of interest P2M1 and P1A1) for the first image region and a second set of keypoints for the second image region; and comparing the first set of keypoints and the second set of keypoints (generating matches C) (Paragraphs 0066, 0068, 0076-0087, 0090-0094).
7. As to claim 27, Dura discloses generating, from the handwriting content field within the input digital image, digital text characters utilizing a handwriting recognition model that focuses on discrete image regions of the input digital image (Paragraphs 0096-0098).
8. As to claim 28, Dura discloses a system (as shown in Figure 2) comprising: at least one processor (processor 12); and one or more memory devices (memory 14) coupled to the at least one processor, the one or more memory devices storing instructions that, when executed by the at least one processor, cause the at least one processor to: determine, for a template image (reference image M1 shown in Figures 4 and 6-7) defining a layout of handwriting content (content of regions of interest Zr) for an image set, template area coordinates (points of interest associated with each region defined by four corners of the regions) defining bounding boxes dividing the template image into template areas; transform the template area coordinates (using transformations T shown in Figures 6-7) to align with dimensions of an input digital image (acquired structured document image A1) within the image set; and determine a location of a handwriting content field (regions Za) within the input digital image by extracting, from the input digital image, landmark coordinates (coordinates of regions Za) indicating locations of handwriting content based on transforming the template area coordinates (Paragraphs 0042-0049, 0062-0070, 0074-0098, a device for analysis of a structured document, shown in Figure 2, includes a processor and memory that execute an operational method, shown in Figure 5, wherein a stored reference/template image defines a layout of content fields where handwriting is present within a specific type of document has the coordinates of the four corners of said fields extracted in order to generate a geometric transformation that characterizes distortions present within the input structured document images including the fields of interest present within the template image such that locations of relevant content fields within the input structured document images to be analyzed are determined through projection of the corresponding reference regions of the reference image onto the input structured document image after application of the determined transformation to the reference image).
9. As to claim 30, Dura discloses transforming the template area coordinates to align with the dimensions of the input digital image comprises extracting a first image region (Zr1-Zr4) from the template image and a second image region (Za1-Za4) from the input digital image; determining, utilizing a keypoint detection model (algorithm performed by image processing module 4), a first set of keypoints (corner coordinates and/or points of interest P2M1 and P1A1) for the first image region and a second set of keypoints for the second image region; and comparing the first set of keypoints and the second set of keypoints (generating matches C) (Paragraphs 0066, 0068, 0076-0087, 0090-0094).
10. As to claim 34, Dura discloses instructions that, when executed by the at least one processor, cause the at least one processor to generate, from the handwriting content field within the input digital image, digital text characters utilizing a handwriting recognition model that focuses on discrete image regions of the input digital image (Paragraphs 0096-0098).
11. As to claim 35, Dura discloses a non-transitory computer readable medium (memory 14) storing instructions that, when executed by at least one processor (processor 12), cause the at least one processor to perform operations (shown in Figure 5) comprising: determining, for a template image (reference image M1 shown in Figures 4 and 6-7) defining a layout of handwriting content (content of regions of interest Zr) for an image set, template area coordinates (points of interest associated with each region defined by four corners of the regions) defining bounding boxes dividing the template image into template areas; transforming the template area coordinates (using transformations T shown in Figures 6-7) to align with dimensions of an input digital image (acquired structured document image A1) within the image set; and determining a location of a handwriting content field (regions Za) within the input digital image by extracting, from the input digital image, landmark coordinates (coordinates of regions Za) indicating locations of handwriting content based on transforming the template area coordinates (Paragraphs 0042-0049, 0062-0070, 0074-0098, a device for analysis of a structured document, shown in Figure 2, includes a processor and memory that execute an operational method, shown in Figure 5, wherein a stored reference/template image defines a layout of content fields where handwriting is present within a specific type of document has the coordinates of the four corners of said fields extracted in order to generate a geometric transformation that characterizes distortions present within the input structured document images including the fields of interest present within the template image such that locations of relevant content fields within the input structured document images to be analyzed are determined through projection of the corresponding reference regions of the reference image onto the input structured document image after application of the determined transformation to the reference image).
12. As to claim 37, Dura discloses transforming the template area coordinates to align with the dimensions of the input digital image comprises extracting a first image region (Zr1-Zr4) from the template image and a second image region (Za1-Za4) from the input digital image; determining, utilizing a keypoint detection model (algorithm performed by image processing module 4), a first set of keypoints (corner coordinates and/or points of interest P2M1 and P1A1) for the first image region and a second set of keypoints for the second image region; and comparing the first set of keypoints and the second set of keypoints (generating matches C) (Paragraphs 0066, 0068, 0076-0087, 0090-0094).
13. As to claim 40, Dura discloses generating, from the handwriting content field within the input digital image, digital text characters utilizing a handwriting recognition model that focuses on corner regions of the input digital image (Paragraphs 0096-0098).
16Claim 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 of this title, 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.
14. Claims 26 and 33 are rejected under 35 U.S.C 103 as being unpatentable over Dura (US PGPub 2018/0285639) [hereafter Dura] in view of Farivar (US PGPub 2020/0005439) [hereafter Farivar].
15. As to claims 26 and 33, it is noted that Dura fails to particularly disclose the keypoint detection model comprises a deep learning model.
On the other hand, Farivar discloses a keypoint detection model comprises a deep learning model (Paragraphs 0006-0007, 0022, 0029-0030).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the invention to include a keypoint detection model comprising a deep learning model as taught by Farivar with the method and system of Dura because the cited prior art are directed towards transforming coordinates of keypoints between images of template and deformed documentation and because each of the claimed limitations are fully disclosed within the combination of the prior art references and would yield predictable results of allowing accurate detection of similar keypoints in both the reference and structured document images through use of a properly trained neural network based machine learning system.
Claim Objections
16. Claims 22, 24-25, 29, 31-32, 36, and 38-39 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
17. Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL S OSINSKI whose telephone number is (571) 270-3949. The examiner can normally be reached on Monday - Friday, 10:00am - 6:00pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Oneal Mistry can be reached on (313) 446-4912. The fax phone number for the organization where this application or proceeding is assigned is (571)-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
MO
/MICHAEL S OSINSKI/Primary Examiner, Art Unit 2674
10/8/2026
Prosecution Insights