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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d).
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/09/24 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hall et al US 10346702 in view of Gokturk et al US 20060253491.
Regarding claim 1, Hall et al teaches A system comprising:
one or more processors (processors 310 (column 7, lines 65-67); and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors (memory 320 (column 7, lines 65-67)), are configured to cause the system to:
receive, from a client device, an image file associated with a first document (system receives or captures an image of a resource document comprising image coordinates. (column 3, lines 48-50).;
extract, from the image file, one or more extractable data entries based on applying a data extraction technique (system then applies a data field-specific OCR process to the provided image coordinate area to extract a value of the data field (column 3, lines 57-60);
determine whether the one or more extractable data entries match stored data entries beyond a predetermined threshold of similarity (compare the extracted value of the data field to a database of previously identified values of the data field from a same source of the resource document or a same type of the resource document, and transmit the extracted value of the data field to a resource processing system in response to determining that the extracted value of the data field matches a previously identified value of the previously identified values (column 2, lines 35-43);
identify one or more incomplete data entries when stored data entries do not match the one or more extractable data entries beyond the predetermined threshold of similarity (the system can determine that the value of the data field is missing, is incomplete, or does not match an expected value or format (threshold of similarity) (column 14, lines 17-22);
automatically replace the one or more incomplete data entries with one or more completed data entries, the one or more completed data entries based on the one or more extractable data entries (the data field-specific OCR process has identified and extracted the value of the missing data field, the process 500 may proceed to block 518, where the system replaces the expected image coordinate area in a database with the expected image coordinate data and associates the stored updated expected image coordinate area for the data field with the identified resource document source or type (column 16, lines 27-35);
identify a signature block within the image file associated with the first document (sample image of the check 700 including several data fields of the check. These data fields include a signature data field 716 (column 21, lines 15-23); and
Hall et al fails to teach verify a presence of a signature associated with a client associated with the client device within the signature block,
Gokturk et al teaches verify a presence of a signature associated with a client associated with the client device within the signature block (a recognition signature may be determined for a given person appearing in one of the cluster of images. The recognition signature may be used in identifying a recognition signature of one or more persons appearing in any one of the cluster of images (paragraph 0035).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: verify a presence of a signature associated with a client associated with the client device within the signature block,
The reason for doing so would be to identify and verify authenticity of an image file
Regarding claim 2, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: identify at least one inconsistent data entry associated with the stored data entries based on comparing the stored data entries to the one or more extractable data entries; and transmit a request to reprocess the first document (Hall et al: the actual value of the missing data field may have been entered incorrectly (e.g., not an appropriate number of characters, incorrect format) or have been damaged (e.g., smeared or washed out ink, and the like), such that the data field-specific OCR process cannot identify and extract an appropriate value. In such cases, the system may request the specialist to provide a new or different coordinate area for the missing data field, or return an error message to at least one component of the managing entity system indicating an unsuccessful attempt at processing the resource document. (column 16, lines 15-26).
Regarding claim 3, Hall et al in view of Gokturk et al teaches wherein the data extraction technique comprises optical character recognition (Hall et al: system then applies a data field-specific OCR process to the provided image coordinate area to extract a value of the data field (column 3, lines 57-60).
Regarding claim 4, Hall et al in view of Gokturk et al teaches wherein the data extraction technique further comprises a neural network model that receives the one or more extractable data entries as input (Gokturk et al: a training phase is applied where a training set of face and non-face images are collected, and a classification algorithm, such as Support Vector Machines, Neural Networks, or Hidden Markov Models, Adaboost classifiers are trained (paragraph 0069).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the data extraction technique further comprises a neural network model that receives the one or more extractable data entries as input,
The reason for doing so would be to accurately identify objects in an image file
Regarding claim 5, Hall et al in view of Gokturk et al teaches wherein extracting the one or more extractable data entries comprises identifying one or more image regions within the image file corresponding to a likely presence of the one or more extractable data entries (Hall et al: The configuration file includes a template for the resource document, including expected coordinate areas or regions of the resource document associated with data fields. Using this configuration file, an OCR process is run on the image of the resource document in an attempt to extract a value of a data field from the expected coordinate area of the resource document (column 10, lines 40-46).
Regarding claim 6, Hall et al in view of Gokturk et al teaches wherein the one or more image regions are identified based on detecting an image object (Gokturk et al: an image file and metadata that identifies one or more objects in the image file (paragraph 0043).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the one or more image regions are identified based on detecting an image object,
The reason for doing so would be to identify objects in an image file
Regarding claim 7, Hall et al et teaches A system comprising:
one or more processors (processors 310 (column 7, lines 65-67); and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors (memory 320 (column 7, lines 65-67)), are configured to cause the system to:
receive an image file associated with a first document (system receives or captures an image of a resource document comprising image coordinates. (column 3, lines 48-50);
selectively extract one or more extractable data entries based on applying a data extraction technique on one or more image regions within the image file corresponding to a likely presence of the one or more extractable data entries (system then applies a data field-specific OCR process to the provided image coordinate area to extract a value of the data field (column 3, lines 57-60). optical character recognition (OCR) engine 120 may be any computing device or set of computing devices configured to scan or read images of documents and identify and extract text, numbers, icons, symbols, security codes, and the like from the documents using an OCR process. In some embodiments, multiple types of OCR processes may be performed by the OCR engine 120. For example, a generic OCR process may be configured to search for, identify, and extract most normal text and numbers in a document (column 4, lines 54-67);
determine whether the one or more extractable data entries match one or more stored data entries beyond a predetermined threshold of similarity (compare the extracted value of the data field to a database of previously identified values of the data field from a same source of the resource document or a same type of the resource document, and transmit the extracted value of the data field to a resource processing system in response to determining that the extracted value of the data field matches a previously identified value of the previously identified values (column 2, lines 35-43); and
Hall et al: fails to teach responsive to the one or more extractable data entries matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as completed, wherein marking the first document as completed further comprises identifying a signature block within the image file associated with the first document and verifying a presence of a signature associated with a client associated with a client device within the signature block
Gokturk et al teaches responsive to the one or more extractable data entries matching the one or more stored data entries beyond the predetermined threshold of similarity (a recognition signature may be determined for a given person appearing in one of the cluster of images. The recognition signature may be used in identifying a recognition signature of one or more persons appearing in any one of the cluster of images (paragraph 0035), mark the first document as completed, wherein marking the first document as completed further comprises identifying a signature block within the image file associated with the first document and verifying a presence of a signature associated with a client associated with a client device within the signature block (Once training is completed, a system may analyze all images for which no recognition has been performed for purpose of detecting persons and determining recognition signatures for detected persons. Upon detecting persons and determining recognition signatures, the determined signatures may be programmatically compared to signature from the training set. Matches may be determined when determined signatures are within a quantitative threshold of the signatures of the training set. Thus, matches may not be between identical signatures, but ones that are deemed to be sufficiently close (paragraph 0147).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: responsive to the one or more extractable data entries matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as completed, wherein marking the first document as completed further comprises identifying a signature block within the image file associated with the first document and verifying a presence of a signature associated with a client associated with a client device within the signature block
The reason for doing so would be to identify and verify authenticity of an image file
Regarding claim 8, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: responsive to the one or more extractable data entries not matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as inconsistent ((Hall et al: the system can determine that the value of the data field is missing, is incomplete, or does not match an expected value or format (threshold of similarity) (column 14, lines 17-22).
Regarding claim 9, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: proactively replace one or more inconsistent data entries of the one or more extractable data entries with a corresponding stored data entry to generate a corrected first document (Hall et al: the data field-specific OCR process has identified and extracted the value of the missing data field, the process 500 may proceed to block 518, where the system replaces the expected image coordinate area in a database with the expected image coordinate data and associates the stored updated expected image coordinate area for the data field with the identified resource document source or type (column 16, lines 27-35).
Regarding claim 10, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: generate and transmit a message to a client device graphically identifying the replaced one or more inconsistent data entries of the one or more extractable data entries (Hall et al: the data field-specific OCR process has identified and extracted the value of the missing data field, the process 500 may proceed to block 518, where the system replaces the expected image coordinate area in a database with the expected image coordinate data and associates the stored updated expected image coordinate area for the data field with the identified resource document source or type (column 16, lines 27-35)..
Regarding claim 11, Hall et al in view of Gokturk et al teaches wherein the message requests to verify the corrected first document (Hall et al: the system displays an outlined and/or highlighted area that indicates the expected coordinate area of the data field within the image of the data field. In this way, the system can show the specialist where the value of the data field was attempted to be extracted, which in turn helps the specialist identify any deficiencies in the expected coordinate area that can be corrected (column 14, lines 43-49).
Regarding claim 12, Hall et al in view of Gokturk et al teaches wherein the one or more image regions are identified based on detecting an image object (Gokturk et al: an image file and metadata that identifies one or more objects in the image file (paragraph 0043).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the one or more image regions are identified based on detecting an image object
The reason for doing so would be to identify and verify authenticity of an image file
Regarding claim 13, Hall et al teaches A system comprising:
one or more processors (processors 310 (column 7, lines 65-67); and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors (memory 320 (column 7, lines 65-67)), are configured to cause the system to:
receive an image file associated with a first document (system receives or captures an image of a resource document comprising image coordinates. (column 3, lines 48-50);
selectively extract one or more extractable data entries based on applying a data extraction technique on one or more image regions within the image file corresponding to a likely presence of the one or more extractable data entries (system then applies a data field-specific OCR process to the provided image coordinate area to extract a value of the data field (column 3, lines 57-60). optical character recognition (OCR) engine 120 may be any computing device or set of computing devices configured to scan or read images of documents and identify and extract text, numbers, icons, symbols, security codes, and the like from the documents using an OCR process. In some embodiments, multiple types of OCR processes may be performed by the OCR engine 120. For example, a generic OCR process may be configured to search for, identify, and extract most normal text and numbers in a document (column 4, lines 54-67),
determine whether the one or more extractable data entries match one or more stored data entries beyond a predetermined threshold of similarity (compare the extracted value of the data field to a database of previously identified values of the data field from a same source of the resource document or a same type of the resource document, and transmit the extracted value of the data field to a resource processing system in response to determining that the extracted value of the data field matches a previously identified value of the previously identified values (column 2, lines 35-43); and
Hall et al fails to teach wherein the one or more image regions are identified based on detecting an image object, and wherein the image object comprises an object selected from a subject header, a signature block, and a presence of an image of a human face;
responsive to the one or more extractable data entries matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as completed
Gokturk et al teaches wherein the one or more image regions are identified based on detecting an image object, and wherein the image object comprises an object selected from a subject header, a signature block, and a presence of an image of a human face (the recognition signature is carried with the header of the image and the user may enter the first and last name of a person he wishes searched, or the user may select that person's face from an objectified image rendering. (paragraph 0270);
responsive to the one or more extractable data entries matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as completed (a recognition signature may be determined for a given person appearing in one of the cluster of images. The recognition signature may be used in identifying a recognition signature of one or more persons appearing in any one of the cluster of images (paragraph 0035).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the one or more image regions are identified based on detecting an image object, and wherein the image object comprises an object selected from a subject header, a signature block, and a presence of an image of a human face;
responsive to the one or more extractable data entries matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as completed
The reason for doing so would be to identify and verify authenticity of an image file
Regarding claim 14, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: responsive to the one or more extractable data entries not matching the one or more stored data entries beyond the predetermined threshold of similarity, mark the first document as inconsistent ((Hall et al: the system can determine that the value of the data field is missing, is incomplete, or does not match an expected value or format (threshold of similarity) (column 14, lines 17-22).
Regarding claim 15, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: proactively replace one or more inconsistent data entries of the one or more extractable data entries with a corresponding stored data entry to generate a corrected first document (Hall et al: the data field-specific OCR process has identified and extracted the value of the missing data field, the process 500 may proceed to block 518, where the system replaces the expected image coordinate area in a database with the expected image coordinate data and associates the stored updated expected image coordinate area for the data field with the identified resource document source or type (column 16, lines 27-35).
Regarding claim 16, Hall et al in view of Gokturk et al teaches wherein the memory stores further instructions that, when executed by the one or more processors, are configured to cause the system to: generate and transmit a message to a client device graphically identifying the replaced one or more inconsistent data entries of the one or more extractable data entries (Hall et al: the data field-specific OCR process has identified and extracted the value of the missing data field, the process 500 may proceed to block 518, where the system replaces the expected image coordinate area in a database with the expected image coordinate data and associates the stored updated expected image coordinate area for the data field with the identified resource document source or type (column 16, lines 27-35).
Regarding claim 17, Hall et al in view of Gokturk et al teaches wherein the message requests to verify the corrected first document (Hall et al: the system displays an outlined and/or highlighted area that indicates the expected coordinate area of the data field within the image of the data field. In this way, the system can show the specialist where the value of the data field was attempted to be extracted, which in turn helps the specialist identify any deficiencies in the expected coordinate area that can be corrected (column 14, lines 43-49).
Regarding claim 18, Hall et al in view of Gokturk et al teaches wherein the image object comprises a subject header (Gokturk et al: the recognition signature is carried with the header of the image (paragraph 0270).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the image object comprises a subject header
The reason for doing so would be to identify objects in image file
Regarding claim 19, Hall et al in view of Gokturk et al teaches wherein the image object comprises a signature block (Gokturk et al: a recognition signature may be determined for a given person appearing in one of the cluster of images. The recognition signature may be used in identifying a recognition signature of one or more persons appearing in any one of the cluster of images (paragraph 0035).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the image object comprises a signature block
The reason for doing so would be to identify objects in image file
Regarding claim 20, Hall et al in view of Gokturk et al teaches wherein the image object comprises a presence of an image of a human face (Gokturk et al: the user may select that person's face from an objectified image rendering. (paragraph 0270);
Therefore, it would have been obvious to one of ordinary skill in the art to modify Hall et al to include: wherein the image object comprises a presence of an image of a human face
The reason for doing so would be to identify a person identified in an image file
Conclusion
Any inquiry concerning this communication should be directed to Michael Burleson whose telephone number is (571) 272-7460 and fax number is (571) 273-7460. The examiner can normally be reached Monday thru Friday from 8:00 a.m. – 4:30p.m. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Akwasi Sarpong can be reached at (571) 270- 3438.
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.
Michael Burleson
Patent Examiner
Art Unit 2681
Michael Burleson
September 5, 2026
/MICHAEL BURLESON/
/AKWASI M SARPONG/ SPE, Art Unit 2681 9/9/2026
Prosecution Insights