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 .
Status of Claims
Claims 1 – 5, 7, 9 – 14, 16, 18 – 20 remain pending.
Claims 1, 10 and 19 are Amended
Claims 6, 8, 15 and 17 have been canceled.
Response to Arguments
Applicant's arguments filed July 08, 2026 with respect to claims 1 – 5, 7, 9 – 14, 16 and 18 – 20 have been considered but are moot because the new grounds of rejection do not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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.
Claims 1, 2, 7, 9 – 11, 16, 18 – 20 are rejected under 35 U.S.C 103 as being unpatentable over Agam et al. US Patent Publication No. US-20070211964-A1 (hereinafter Agam) in view of Sangala US Patent Application Publication No. US-11106891-B2 (hereinafter Sangala), Withrow US Patent Publication No. US-10614302-B2 (hereinafter Withrow) and Arnold Patent Publication No. US-10769360-B1 (hereinafter Arnold).
Regarding claim 1, Agam discloses a computer-implemented method for pre-processing signature data to improve alignment of training data, the computer-implemented method comprising: accessing, via one or more processors, a corpus of signed documents (Agam in [0005] discloses, “given a large collection of documents ... such as signatures of a specific person, or containing a certain logo or stamp, or containing a certain handwritten word”. Furthermore, Agam in [0027] discloses about signature alignment, “The standard position is a position in which the signature is aligned with the horizontal axis, its center of mass is located at the origin"); identifying a portion of image data in a signed document that represents a signature (Agam in Fig. 1 discloses about extracting signatures from document images equates to identifying the portion of image that represent signature); and training, via the one or more processors, a signature type classifier using the extracted signatures (Agam in [0002] discloses about classifying different signature type and [0014] discloses about training the images).
Agam doesn’t disclose about the following limitation as further recited in the claim.
Sangala discloses about extracting, via the one or more processors, the portions of the image data that represent the identified signatures (Sangala in [Column – 6, Line 4 – 12] discloses, “a bounding box contains a signature may be determined, and in a signed document, a particular box ... The identified regions of the image within the identified bounding boxes are extracted (Step 260 ) for subsequent use in verification”); processing, via the one or more processors, the extracted signatures to align the portions of the image data by: detecting a skew associated with a respective portion of the image data, and correcting the skew for the respective portion of the image data (Sangala in [Column – 4, Line 31 – 36] discloses, “The image may also undergo deskewing (Step 212 ) to rotate the entire image or portions thereof, compensating for a document that was entered into a scanner askew, printed at an angle to the underlying paper or substrate, or otherwise caused to have its contents non-horizontal within the captured image” wherein deskewing a portion of an image like bounding box containing a signature (disclosed in [Column – 6, Line 4 – 12]) you have to extract the portion of the image then you have to deskew it. The extraction of the portion of the image comes first before deskewing that signature portion).
It would have been obvious to one with one having an ordinary skill in art before the
effective filling date of the claimed invention to integrate the technique of Sangala into the system of Agam because aligning the signature will ensure that all the signature training set have consistent position and orientation resulting in more accurate classification model.
Agam and Sangala in the combination doesn’t disclose about the following limitation as further recited in the claim.
Withrow discloses generating, via the one or more processors, a signature vector that includes the extracted signature data; inputting, via the one or more processors, the signature data from the signature vector into a text extraction library, wherein the text extraction library produces signature data that is a subset of the extracted signature data (Withrow in [Column – 24, Line 11 – 19] discloses, “at least one location of interest within the authentication region, a method for extracting a feature vector characterizing the location of interest, and a method for comparing the extracted feature vector to a reference feature vector; based on the fingerprint template, identify a subset of the image data corresponding to the authentication region; based on the fingerprint template, extract a feature vector from the subset of the image data; and store extracted feature vector data defining the extracted feature vector in a database”).
It would have been obvious to one with one having an ordinary skill in art before the
effective filling date of the claimed invention to integrate the technique of Withrow into the system of Agam in view of Sangala because it would allow the system to filter out the noise in the signature data to produce a cleaner and more reliable subset signature data.
Agam, Sangala and Withrow in the combination doesn’t disclose about the following limitation as further recited in the claim.
Arnold discloses the signature type classifier is configured to classify an input signature as one of a plurality of signature types based upon how the signature was created (Arnold in [Column – 1, Line 25 – 29] discloses about plurality of signature type, “Some of these items need to be wet-signed (e.g., using a pen with ink), while others can be electronically signed or e-signed using a computer automated service, such as DocuSign®, HelloSign® or Adobe Sign®”. Furthermore, Arnold in [Column – 1, Line 43 – 49] discloses about categorizing (classifying) electronic-sign item or a wet-sign item (electronic or handwritten signature), “Each signing item is categorized as an electronic-sign item or a wet-sign item. A first electronic document is produced with pages from the electronic document that have electronic-sign items and a second electronic document is produced with pages from the electronic document that have wet-sign items”).
It would have been obvious to one with one having an ordinary skill in art before the
effective filling date of the claimed invention to integrate the technique of Arnold into the system of Agam in view of Sangala and Withrow because it would allow the system to reject a document that contains the wrong type of signature and accept one that uses the authorized type. The step increases the accuracy in signature type verification and decreases the need for manual review.
Summary of Citations (Arnold)
[Column – 1, Line 25 – 29]; “Some of these items need to be wet-signed (e.g., using a pen with ink), while others can be electronically signed or e-signed using a computer automated service, such as DocuSign®, HelloSign® or Adobe Sign®”.
[Column – 1, Line 43 – 49]; “Each signing item is categorized as an electronic-sign item or a wet-sign item. A first electronic document is produced with pages from the electronic document that have electronic-sign items and a second electronic document is produced with pages from the electronic document that have wet-sign items”.
Summary of Citations (Withrow)
[Column – 24, Line 11 – 19]; “at least one location of interest within the authentication region, a method for extracting a feature vector characterizing the location of interest, and a method for comparing the extracted feature vector to a reference feature vector; based on the fingerprint template, identify a subset of the image data corresponding to the authentication region; based on the fingerprint template, extract a feature vector from the subset of the image data; and store extracted feature vector data defining the extracted feature vector in a database”.
Summary of Citations (Agam)
Paragraph [0002]; “More particularly the present invention addresses the problem of indexing and classifying images, e.g., signatures, logos, stamps, or word spotting, i.e., word identification within an image”.
Paragraph [0005]; “given a large collection of documents, e.g., such as those commonly related to legal investigations; and the task of obtaining those documents containing homolog images, such as signatures of a specific person, or containing a certain logo or stamp, or containing a certain handwritten word”.
Paragraph [0014]; “Using a training set of images with similar characteristics to the collection to be processed, in this case similar signatures, whether numerous iterations of the representative image or just a random set of cursive script signatures sufficient for training; the present invention will determine which comparison parameters are most discerning of, or discriminatory for the candidate selection algorithm, i.e., identifying those signatures which are candidates for retrieval on the stored documents within the database; i.e., those images which are closest to the representative signature during a comparison”.
Paragraph [0027]; “The standard position is a position in which the signature is aligned with the horizontal axis, its center of mass is located at the origin, and the size of the long side of the bounding box containing it is 1”.
Summary of Citations (Sangala)
[Column – 4, Line 31 – 36]; “The image may also undergo deskewing (Step 212 ) to rotate the entire image or portions thereof, compensating for a document that was entered into a scanner askew, printed at an angle to the underlying paper or substrate, or otherwise caused to have its contents non-horizontal within the captured image”.
[Column – 6, Line 4 – 12]; “Based on these factors, an overall confidence level or likelihood that a bounding box contains a signature may be determined, and in a signed document, a particular box ... The identified regions of the image within the identified bounding boxes are extracted (Step 260) for subsequent use in verification”.
[Column – 7, Line 4 – 9]; “conversion of received image data to grayscale, despeckling the image data, removing horizontal and vertical lines from the data via convolution matrix, cropping the image to remove whitespace, rotating the image if the signature is aligned at an angle rather than horizontal, via a deskewing algorithm, and binarization”.
[Column – 6, Line 10 – 12]; “The identified regions of the image within the identified bounding boxes are extracted (Step 260) for subsequent use in verification”.
Regarding claims 2 and 7, the combination of Agam, Sangala, Withrow and Arnold as a whole teaches claim 1, and Sangala teaches claim 2 and 7 for the same grounds of rejection from the Non-Final Office Action of 04/08/2026.
Regarding claim 9, the combination of Agam, Sangala, Withrow and Arnold as a whole teaches claim 1, and Agam teaches claim 9 for the same grounds of rejection from the Non-Final Office Action of 04/08/2026.
Regarding claim 10, apparatus claim 10 corresponds to method claim 1. Therefore, the rejection analysis and motivation to combine of claim 1 is applicable to claim 10.
Regarding claim 11, apparatus claim 11 corresponds to method claim 2. Therefore, the rejection analysis and motivation to combine of claim 2 is applicable to claim 11.
Regarding claim 16, apparatus claim 16 corresponds to method claim 7. Therefore, the rejection analysis and motivation to combine of claim 7 is applicable to claim 16.
Regarding claim 18, is a non-transitory computer readable storage medium claim
corresponds to method claim 9. Therefore, the rejection analysis of claim 9 is applied in claim
18.
Regarding claim 19, is a non-transitory computer readable storage medium claim
corresponds to method claim 1. Therefore, the rejection analysis of claim 1 is applied in claim
19.
Regarding claim 20, is a non-transitory computer readable storage medium claim
corresponds to method claim 9. Therefore, the rejection analysis of claim 9 is applied in claim
20.
Claims 3 – 5 and 12 – 14 are rejected under 35 U.S.C 103 as being unpatentable over Agam in view of Sangala, Withrow and Arnold and further in view of Chou US Patent Application Publication No. US-20240211638-A1 (hereinafter Chou).
Regarding claims 3 – 5 and 12 – 14, the combination of Agam, Sangala, Withrow and Arnold as a whole teaches claim 1 but fails to teach the further limitations as recited in claims 3 – 5 and 12 – 14. Chou teaches claims 3 – 5 and 12 – 14 for the same grounds of rejection and motivation established in the Non-Final Office Action of 04/08/2026.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZAID MUHAMMAD SALEH whose telephone number is (703)756-1684. The examiner can normally be reached M-F 8 am - 5 pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vu Le can be reached on (571)272-7332. 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.
/ZAID MUHAMMAD SALEH/
Examiner, Art Unit 2668
08/06/2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights