# US 12,217,526 B2 · Validating identification documents > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,526 B2 - Document ID: US12217526B2 - Status: Granted - Kind: B2 - Application number: 18/469,352 - Filed: 2023-09-18 - Published: 2024-01-04 - Granted: 2025-02-04 - Earliest claimed: 2021-06-25 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Jason Pribble; Daniel Alan Jarvis; Swapnil Patil - Web page: https://patentgrep.com/patent/US12217526B2 ## CPC - G06V 30/418: Document matching, e.g. of document images - G06K 7/1413: {1D bar codes} - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06V 10/82: using neural networks - G06V 30/413: Classification of content, e.g. text, photographs or tables - G06V 40/168: {Feature extraction; Face representation} - G06V 40/33: {based only on signature image, e.g. static signature recognition} - G06V 30/10: Character recognition - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06K: GRAPHICAL DATA READING (image or video recognition or understanding G06V); PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS ## Abstract The method, system, and non-transitory computer-readable medium embodiments described herein are directed to verifying documents. In various embodiments, a server may receive a first image of a front-side of a document. The server may extract a first feature of the front-side of the document from the first image and identify a first environmental feature from the first image. The server may receive a second image of a backside of the document and identify a second feature of the backside of the document from the second image. The server may also identify a second environmental feature from the second image. The server may verify the document by confirming that the first feature matches the second feature and the first environmental feature matches the second environmental feature. ## Claims ### Claim 1 A method to validate a document, the method comprising: receiving, by a processor, a first image of a front-side of the document; identifying, by the processor, a type of the document using a machine learning algorithm based on the first image; extracting, by the processor, a first feature of the front-side of the document from the first image; identifying, by the processor, a first environmental feature from the first image, the first environmental feature being related to a capture of the first image by a camera; receiving, by the processor, a second image of a backside of the document; confirming, by the processor, the type of the document using the machine learning algorithm based on the second image; identifying, by the processor, a second feature of the backside of the document from the second image; identifying, by the processor, a second environmental feature from the second image, the second environmental feature being related to a capture of the second image by the camera; and verifying, by the processor, the document by confirming that the first feature matches the second feature, the first environmental feature matches the second environmental feature, and that the type of document is the same in the first and second image, wherein the first environmental feature and second environmental feature include at least one of: lighting, resolution, or color balance. ### Claim 2 (depends on 1) The method of claim 1, wherein the identifying of the second feature of the backside of the document from the second image comprises scanning a barcode on the backside of the document as displayed in the second image. ### Claim 3 (depends on 1) The method of claim 1, wherein the first feature includes an imperceptible data. ### Claim 4 (depends on 3) The method of claim 3, further comprising extracting, by the processor, the imperceptible data based on a bitmap of each pixel in the first image. ### Claim 5 (depends on 1) The method of claim 1, wherein the first environmental feature and second environmental feature further include a background, and identifying the background comprises: identifying, by the processor, a boundary of the document in the first and second image; and identifying, by the processor, a surface outside the boundary of the document in the first and second image. ### Claim 6 (depends on 1) The method of claim 1, wherein the first feature and the second feature each include at least one of: name, date of birth, height, organ donor status, hair color, eye color, or address. ### Claim 7 (depends on 1) The method of claim 1, wherein verification of the document indicates that the front-side of the document and the backside of the document correspond to a same document. ### Claim 8 (depends on 1) The method of claim 1, further comprising: extracting, by the processor, a first facial image of a user associated with the document from the first image; extracting, by the processor, a second facial image of the user associated with the document from the second image; and matching, by the processor, the first facial image to the second facial image. ### Claim 9 (depends on 1) The method of claim 1, further comprising: extracting, by the processor, a first signature disposed on the front-side of the document from the first image; extracting, by the processor, a second signature disposed on the backside of the document from the second image; and matching, by the processor, the first signature with the second signature. ### Claim 10 A system to validate a document, the system comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor configured to: receive a first image of a front-side of the document; identify a type of the document using a machine learning algorithm based on the first image; extract a first feature of the front-side of the document from the first image; identify a first environmental feature from the first image, the first environmental feature being related to a capture of the first image by a camera; receive a second image of a backside of the document; confirm the type of the document using the machine learning algorithm based on the second image; identify a second feature of the backside of the document from the second image; identify a second environmental feature from the second image, the second environmental feature being related to a capture of the second image by the camera; and verify the document by confirming that the first feature matches the second feature, the first environmental feature matches the second environmental feature, and that the type of document is the same in the first and second image, wherein the first environmental feature and second environmental feature include at least one of: lighting, resolution, or color balance. ### Claim 11 (depends on 10) The system of claim 10, wherein the identifying of the second feature of the backside of the document from the second image comprises scanning a barcode on the backside of the document as displayed in the second image. ### Claim 12 (depends on 10) The system of claim 10, wherein the first feature includes an imperceptible data; and the at least one processor is further configured to extract the imperceptible data based on a bitmap of each pixel in the first image. ### Claim 13 (depends on 10) The system of claim 10, wherein the first environmental feature and second environmental feature further include a background, and identifying the background comprises: identifying a boundary of the document in the first and second image; and identifying a surface outside the boundary of the document in the first and second image. ### Claim 14 (depends on 10) The system of claim 10, wherein the first feature and the second feature each include at least one of: name, date of birth, height, organ donor status, hair color, eye color, or address. ### Claim 15 (depends on 10) The system of claim 10, wherein verification of the document indicates that the front-side of the document and the backside of the document correspond to a same document. ### Claim 16 (depends on 10) The system of claim 10, wherein the at least one processor is further configured to: extract a first facial image of a user associated with the document from the first image; extract a second facial image of the user associated with the document from the second image; and match the first facial image to the second facial image. ### Claim 17 A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations, the operations comprising: receiving a first image of a front-side of a document; identifying a type of the document using a machine learning algorithm based on the first image; extracting a first feature of the front-side of the document from the first image using optical character recognition (OCR); identifying a first environmental feature from the first image, the first environmental feature being related to a capture of the first image by a camera; receiving a second image of a backside of the document; confirming the type of the document using the machine learning algorithm based on the second image; identifying a second feature of the backside of the document from the second image; identifying a second environmental feature from the second image, the second environmental feature being related to a capture of the second image by the camera; and verifying the document by confirming that the first feature matches the second feature, the first environmental feature matches the second environmental feature, and that the type of document is the same in the first and second image, wherein the first environmental feature and second environmental feature include at least one of: lighting, resolution, or color balance. ### Claim 18 (depends on 17) The non-transitory computer-readable medium of claim 17, wherein the identifying of the second feature of the backside of the document from the second image comprises scanning a barcode on the backside of the document as displayed in the second image. ### Claim 19 (depends on 17) The non-transitory computer-readable medium of claim 17, wherein the first environmental feature and second environmental feature further include a background, and identifying the background comprises: identifying a boundary of the document in the first and second image; and identifying a surface outside the boundary of the document in the first and second image. ### Claim 20 (depends on 17) The non-transitory computer-readable medium of claim 17, wherein verification of the document indicates that the front-side of the document and the backside of the document correspond to a same document.