DETAILED ACTION
Response to Amendment
Applicant’s response to the last Office Action, filed on 7/9/2026 has been entered and made of record.
Examiner maintains the current prior art of record; accordingly, this action is made Final.
The rejection under 35 USC 112(b) is removed in view of amendments.
Response to Arguments
Applicant's arguments filed on 7/9/2026 have been fully considered but they are not persuasive.
In response to the newly amended claim language Examiner has clarified the teachings of the Goodsitt reference. The claims require replacing original image content depicting a text value of each detected region of each original electronic document with the corresponding generated random image to create a modified plurality of electronic document images. Gooditt at paragraph spanning cols. 13 and 14, col. 14, ¶ 5 and col. 15, ¶ 4-6 teaches a template generated directly from the individual original electronic documents. The background original image content of those original images is maintained and the certain text fields are replaced with generated content. The process populates the replacement text images into the driver’s license template for replacement of the existing images. Applicant’s argues, “the input fields start out blank and are ‘populate[d]" by the "template populator.’ There is no original image content being replaced in Goodsitt, let alone original image content depicting a text value.” These arguments are inconsistent with the Goodsitt reference since Goodsitt’s template itself is composed of original image content. The reference is clear that the original image content of the documents is being replaced.
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.
Claim(s) 1, 6, 9, 14 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Goodsitt (US Pat. No. 10,482,174) in view of Chen (US 10,262,235 B1)
Regarding claim 1, Goodsitt discloses a computer-implemented method of training a machine learning model for processing an electronic document, comprising: (Goodsitt teaches a technique for generating synthetic documents in order to provide training data for a machine learning system which analyses images of documents such as driver’s licenses, See Abstract and col. 4, ¶ 3.)
detecting a region for each of a plurality of original electronic documents using a bounding box detection mechanism; (paragraph spanning cols. 12 and 13 teaches detecting the bounds of regions of text boxes.)
generating a random replacement image for each region of the plurality of original electronic documents utilizing a script; (Col. 13, second paragraph from bottom, teaches generating synthetic text imagery for replacement in the driver’s license template. Paragraph spanning cols. 4 and 5 as well as col. 10 second paragraph from bottom teaches that this is based on a random replacement.)
replacing original image content depicting a text value of each detected region of each original electronic document with the corresponding generated random image to create a modified plurality of electronic document images; (Paragraph spanning cols. 13 and 14, col. 14, ¶ 5 and col. 15, ¶ 4-6 teach a template generated directly from the individual original electronic documents. The background original image content of those original images is maintained and the certain text fields are replaced with generated content. The process populates the replacement text images into the driver’s license template for replacement of the existing images.)
generating a training set comprising the modified plurality of electronic document images; and (col. 14, ¶ 2 teaches generating the synthetic training set.)
training the machine learning model using the training set. (col. 15, ¶ 7 teaches training the machine learning model.)
In the field of machine-learning document processing Chen teaches that said region is a magnetic ink character recognition (MICR) region (Chen col. 16, ¶ 2 teaches that a neural network is trained on generated images of portions of a MICR line on a check document. The MICR line is text which contains the bank account and routing number.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Goodsitt’s machine-learning document processing with Chen’s machine-learning document processing. Goodsitt teaches a technique for replacing text images in documents in order to generate synthetic training data. Goodsitt does not expressly teach doing so for bank check documents. Chen teaches using replaced text images in documents generated to provide synthetic training data for bank check documents. The concept of simply applying Goodsitt’s system for generating synthetic training data in a different document type cannot be considered a non-obvious improvement in view of the relevant prior art here. Using known engineering design, no “fundamental” operating principle of the teachings are changed; they continue to perform the same functions as originally taught prior to being combined.
Regarding claim 6, the above combination discloses the computer-implemented method of claim 1, wherein the creating the training set comprises combining the modified plurality of electronic documents with a second plurality of unmodified electronic documents from a database. (Goodsitt col. 4, ¶ 2 teaches combining the modified synthetic and real images for the training set.)
Claims 9 and 14 are the apparatus claims corresponding to the method of claims 1 and 6. Goodsitt teaches an apparatus with a processor and memory (paragraph spanning cols. 6 and 7). Remaining limitations are rejected similarly. See detailed analysis above.
Claim 17 is the non-transitory computer readable medium claim corresponding to the method of claim 1. Goodsitt teaches a computer readable medium (paragraph spanning cols. 6 and 7). Remaining limitations are rejected similarly. See detailed analysis above.
Claim(s) 2-5, 7, 8, 10-13, 15-16 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Goodsitt (US Pat. No. 10,482,174) in view of Chen (US 10,262,235 B1) and Hu (US 20230316792 B1).
Regarding claim 2, the above combination discloses the computer-implemented method of claim 1, including generating the random replacement image for each MICR region (See rejection of claim 1.)
In the field of machine-learning document processing Hu teaches selecting one or more parameters for each region at random; determining a size of each region; and assembling a replacement image for each region based on the selected parameters and the size of the detected region. (Chen teaches generating synthetic training images containing replaced text in the image content. ¶ 0080 and 0081 teach generating on the basis of random parameters (text characters) and based on determining the region size (text length) to assemble the text image on this basis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the above combination’s machine-learning document processing with Hu’s machine-learning document processing. Goodsitt teaches a technique for replacing text images on a random basis in documents in order to generate synthetic training data. Hu expressly teaches the random replaced text images are generated on the basis of their size and their randomized text. The concept of simply applying Hu’s system for generating synthetic training data based on size and other parameters cannot be considered a non-obvious improvement in view of the relevant prior art here. Using known engineering design, no “fundamental” operating principle of the teachings are changed; they continue to perform the same functions as originally taught prior to being combined.
Regarding claim 3, the above combination discloses the computer-implemented method of claim 2, wherein the MICR region comprises a routing number, account number, or serial number. (See rejection of Chen in claim 1.)
Regarding claim 4, the above combination discloses the computer-implemented method of claim 3, wherein the one or more parameters comprises at least a sequence length and a number sequence. (See rejection of claim 2 which teaches that Hu’s random parameter comprises a number sequence. Goodsitt and Chen in rejection of claim 1 both also teaches synthesizing a number sequence. Examiner notes that the claimed list must be interpreted disjunctively in light of the specification, which is consistent with Fujifilm Corp. v. Motorola Mobility LLC, No. 12-CV-03587-WHO, 2015 WL 1265009 (N.D. Cal. Mar 19, 2015) which explained that, unlike the “’at least one of” phrase in SuperGuide Corp. v. DirecTV Enters., Inc., 358 F.3d 870 (Fed. Cir. 2004), which concerned a list of categories of many possible values that users must choose, the list in the instant case involves modes of operation.)
Regarding claim 5, the above combination discloses the computer-implemented method of claim 4, wherein the assembling the replacement image comprises: retrieving a random MICR character image from a database for each character of the selected number sequence; and joining the character images sequentially based on the selected number sequence. (See Hu ¶ 0084 and Fig. 1 regarding rendering character font images sequentially to form text from a database.)
Regarding claim 7, the above combination discloses the computer-implemented method of claim 1, further comprising: applying a destructive technique to each modified electronic document. (Hu ¶ 0092 teaches destructive techniques for the synthetic training data such as inverting colors and adding noise filters.)
Regarding claim 8, the above combination discloses the computer-implemented method of claim 7, wherein the destructive technique comprises at least one of the following: inverting the colors of the modified electronic document; applying a grain filter to the modified electronic document; adding a synthetic ink streak to the modified electronic document; and removing standard sections of the modified electronic document. (See rejection of claim 7. Examiner notes that the claimed list must be interpreted disjunctively in light of the specification, which is consistent with Fujifilm Corp. v. Motorola Mobility LLC, No. 12-CV-03587-WHO, 2015 WL 1265009 (N.D. Cal. Mar 19, 2015) which explained that, unlike the “’at least one of” phrase in SuperGuide Corp. v. DirecTV Enters., Inc., 358 F.3d 870 (Fed. Cir. 2004), which concerned a list of categories of many possible values that users must choose, the list in the instant case involves modes of operation.)
Claims 10-13 and 15-16 are the apparatus claims corresponding to the method of claims 2-4 and 7-8. Goodsitt teaches an apparatus with a processor and memory (paragraph spanning cols. 6 and 7). Remaining limitations are rejected similarly. See detailed analysis above.
Claims 18-20 are the non-transitory computer readable medium corresponding to the method of claims 2-4. Goodsitt teaches a computer readable medium (paragraph spanning cols. 6 and 7). Remaining limitations are rejected similarly. See detailed analysis above.
Conclusion
Based on these facts, 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 extension fee 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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Raphael Schwartz whose telephone number is (571)270-3822. The examiner can normally be reached Monday to Friday 9am-5pm CT.
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, Vincent Rudolph can be reached at (571) 272-8243. 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.
/RAPHAEL SCHWARTZ/ Examiner, Art Unit 2671
