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 .
Election/Restrictions
Claims 9-13 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected group, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on 9/9/2026. Therefore, the restriction is made final herein.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
It is noted that claims 1-8, 14 and 15 are considered eligible subject matter. Even if the claims could be interpreted as an abstract idea, the claims provide limitations that provide a practical application, i.e. document type identification.
Claim Objections
The claims are objected to because they include reference characters which are not enclosed within parentheses.
Reference characters corresponding to elements recited in the detailed description of the drawings and used in conjunction with the recitation of the same element or group of elements in the claims should be enclosed within parentheses so as to avoid confusion with other numbers or characters which may appear in the claims. See MPEP § 608.01(m).
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-8 and 14-15 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the limitation "said embedding vector" in line 19. It is unclear as to which embedding vector the applicant is referring to because each ROI is represented by an embedding vector.
Claim 2 recites the limitation “said convolutional network” in line 4. There are multiple CNN’s previously claimed, so it is unclear as to which one the applicant is referring to.
Claim 5 recites the limitation “their” in line 3. It is unclear as to what “their” is referring to.
Claim 6 recites the limitation "said learned information of said types”" in line 2. There is insufficient antecedent basis for this limitation in the claim. The examiner believes the applicant may be referring to “said learned types”.
Claim 6 recites the limitation "said convolutional network" in lines 4-5. There are multiple CNN’s previously claimed, so it is unclear as to which one the applicant is referring to.
Claim 6 recites the limitation “said portions from images” in lines 8-9. There is insufficient antecedent basis for this limitation in the claim.
Claim 8 recites the limitation "said convolutional neural network" in line 1. There are multiple CNN’s previously claimed, so it is unclear as to which one the applicant is referring to.
Claim 8 recites the litmaiton “said embedding vector” in line 2. There are multiple embedding vectors previously claimed, so it is unclear as to which one the applicant is referring to.
Regarding claim 14, the phrase "such as" renders the claim indefinite because it is unclear whether the limitations following the phrase are part of the claimed invention. See MPEP § 2173.05(d).
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.
Claims 1, 4, 14 and 15 are rejected under 35 U.S.C. 103(a) as being unpatentable over U.S. Patent Application Publication No. 20220180113 (Patel et al) in view of U.S. Patent NO. 11341605 (Singh et al), U.S. Patent Application Publication No. 20140180981 (Dolev et al) and U.S. Patent Application Publication NO. 20080118151 (Bouguet et al).
Regarding claim 1, Patel et al discloses a method (fig. 2A) for classifying a type of identification (ID) document by way of Artificial Intelligence (AI) deep learning to associate and identify the ID document, an ID (fig. 2A) against learned types from a captured image or picture of the ID document (fig. 2A ,item 202), wherein the method comprises an inference phase (fig. 2A, item 202-204), consisting of: detection steps (fig. 2A, item 204): by way of a detection module 1, applying an algorithm identify location information comprising bounding box information and corner information, corner coordinates of said ID document in said image (fig. 2A, item 204); by way of additional modules, producing a normalized ID document image with correct orientation by identifying regions for cropping (page 4, paragraph 47); and Identification steps (fig. 2A-2C, items 204, 216): by way of an identification module 1, performing Region of Interest (ROI) cropping on corrected said normalized ID document image (page 4, paragraph 47), and representing each said ROI by an embedding vector, i.e. the embedding vector that is identified in the NN (page 5, paragraph 51) ; and by way of additional modules, identifying the vector and classifying the document (page 5, paragraph 51).
Patel et al does not disclose expressly an algorithm to identify location information for the document is a CNN, that producing a normalized document image with correct orientation: by way of a detection module 2, selecting corners and normalizing said document in said image 101 from said location information (corners, bounding box) to produce a normalized document image; by way of a detection module 3, applying an orientation classification CNN to said normalized ID document image to correctly orient said captured image; and that in identifying the vector and classifying the document: by way of an identification module 2, applying a nearest neighbor search within a reference database using said embedding vector, and from results of said search, and presenting a list of ID document types ranked according to a most probable match of the ID document to learned types in said reference database.
Singh et al discloses an algorithm to identify location information for the document is a CNN (fig. 5, item 510, col. 12, lines 40-45), and that producing a normalized document image with correct orientation: by way of a detection module 2, selecting corners and normalizing said document in said image 101 from said location information to produce a normalized document image by modifying the image based on homography (fig. 5, item 520); by way of a detection module 3, applying an orientation classification CNN to said normalized document image to correctly orient said captured image (fig. 5, item 525, col. 9, lines 62-66).
Patel et al and Singh et al are combinable because they are from the same field of endeavor, i.e. document processing.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to normalize and find orientation of the document image.
The suggestion/motivation for doing so would have been to provide a more robust system by accounting for distortions and camera angle.
Patel et al (as modified by Singh et al ) does not disclose expressly and that in identifying the vector and classifying the document: by way of an identification module 2, applying a nearest neighbor search within a reference database using said embedding vector, and from results of said search, and presenting a list of ID document types ranked according to a most probable match of the ID document to learned types in said reference database.
Dolev et al discloses that in identifying the vector and classifying the document: by way of an identification module 2, applying a nearest neighbor search within a reference database/ training documents using said embedding vector (page 6, paragraph 126-133, fig. 5, item 420), and from results of said search, and presenting a ID document type according to a most probable match of the ID document to learned types in said reference database (fig. 5, item 440), and the match is of the ID document type (fig. 5).
Patel et al (as modified by Singh et al ) and Dolev et al are combinable because they are from the same field of endeavor, i.e. document identification.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to use a nearest neighbor search.
The suggestion/motivation for doing so would have been to provide a faster, more robust system by using a known way of classifying data.
Patel (as modified by Singh et al and Dolev et al) does not disclose expressly outputting a list of matches ranked.
Bouguet et al discloses outputting a list of matches ranked (page 3, paragraph 36).
Patel (as modified by Singh et al and Dolev et al) & Bouguet et al are combinable because they are from the same field of endeavor, i.e. kNN matching.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to output a list ranked, instead of just the top match.
The suggestion/motivation for doing so would have been to provide a more robust method by allowing the user to view multiple options.
Therefore, it would have been obvious to combine the method of Patel et al with region of interest aligner of Singh et al, the nearest neighbor document ID match of Dolev et al and the output of a list of Bouguet et al to obtain the invention as specified in claim 1.
Regarding claim 4, Patel et al discloses said type indicates one of: a country, a state, or city, and an issuing agency, department, or bureau, because passport, a driving license, a unique identification Document (UID), a membership cards indicate a country, a state, or city, and an issuing agency, department, or bureau, (page 5, paragraph 51).
Regarding claim 14, Patel et al discloses transmitting data via a network communicatively coupled to the electronic device (fig. 1, item 100) and the reference database (Fig. 1, item 108) to an Artificial Intelligence (AI) deep learning machine for performing said detection steps and said identification steps (fig. 1, item 104, 102). Dolev et al discloses presenting the match of ID document types according to the most probable match of the ID document to learned types in said reference database (fig. 5, item 440). Bouguet et al discloses outputting a list of matches ranked (page 3, paragraph 36). Singh et al discloses transmitting the image (fig. 8, item 1 uploaded with item 830) via a network(fig. 89, item 107) to the electronic device (fig. 8, item 100) whereby an electronic device, such as a kiosk, is equipped with a scanner used for capturing the image of the ID document (col. 11, line 65)
Regarding claim 15, Patel et al discloses the AI deep learning machine as part of a device that carries out document processing (fig. 1). Singh et al discloses a device that captures images (fig. 8, item 104) coupled to an electronic device that carries out the document processing (fig. 8,m item 100) each comprise: one or more central processing units (CPUs) (Fig. 11, item 1110 fig. 8, item 112) for executing computer program instructions (fig. 11, item 1120, fig. 8, item 112); a memory for storing at least the computer program instructions and data (fig. 11, item 1125, fig. 9, item 112); a power supply unit (PSU) for providing power to electronic components of the machine, that which runs the machine of fig. 11 and 8; a network interface for transmitting and receiving communications and data (fig. 11, item 1140, fig. 8, interface between 104 and 100); and a user interface for interoperability (fig. 11, item 1110, fig. 9, item 104).
Allowable Subject Matter
Claims 2, 3, 5-8 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.
Claim 2 contains allowable subject matter regarding the claimed image represented by the claimed RGB vector, and said ROI cropping of the claimed identification module 1 is by way of a CNN including layering of RGB component vectors for each ROI, and the CNN of ROI cropping includes laying of RGB component vectors for each ROI and further the CNN of ROI cropping applies convolution kernels on said RGB component vectors to capture spatial and temporal dependencies of RGB pixels.
Claim 5 contains allowable subject matter regarding the claimed reference database is elastically configured, by way of the claimed identification module 1 to add new documents and remove obsolete documents for recognition of their type, through addition and removal of embedding vectors in a table in said reference database without re-training.
Claim 6 contains allowable subject matter regarding the method further comprising a training phase for acquiring said learned information of said types of said ID document in said reference database, consisting of: the claimed detection modules 1 and 3, and the claimed identification module 1 applying the supervised and unsupervised learning, as claimed.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Kathleen Yuan Dulaney whose telephone number is (571)272-2902. The examiner can normally be reached M-F: 9AM-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, Emily Terrell can be reached at 5712703717. 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.
/KATHLEEN Y DULANEY/Primary Examiner, Art Unit 2666 9/22/2026
