US 12,444,213 B1
Machine-learning models for image processing
Ashutosh K. Sureka, Irving, TX (US); Venkata Sesha Kiran Kumar Adimatyam, Irving, TX (US); Miriam Silver, Tel Aviv (IL); and Daniel Funken, Irving, TX (US)
Assigned to CITIBANK, N.A., New York, NY (US)
Filed by Citibank, N.A., New York, NY (US)
Filed on Mar. 19, 2025, as Appl. No. 19/084,341.
Application 19/084,341 is a continuation of application No. 18/629,301, filed on Apr. 8, 2024, granted, now 12,260,657.
Int. Cl. G06V 20/00 (2022.01); G06T 5/60 (2024.01); G06T 7/00 (2017.01); G06V 30/18 (2022.01); G06V 30/19 (2022.01); G06V 30/418 (2022.01); G06V 30/42 (2022.01)
CPC G06V 20/95 (2022.01) [G06T 5/60 (2024.01); G06T 7/0002 (2013.01); G06V 30/18 (2022.01); G06V 30/191 (2022.01); G06V 30/418 (2022.01); G06V 30/42 (2022.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30168 (2013.01); G06T 2207/30176 (2013.01); G06V 2201/10 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for remotely processing document imagery, the method comprising:
receiving, by a computer remote from a user device, via one or more networks, a video feed comprising a plurality of frames from the user device, at least one frame including image data depicting an object;
executing, by the computer, an object recognition engine of a machine-learning architecture using the image data of the plurality of frames, the object recognition engine trained for detecting content data of a document in the image data;
generating, by the computer, a risk score based upon a distance of the content data to a predefined template to validate the content data, wherein the predefined template comprises a plurality of fields comprising a plurality of characters; and
generating, by the computer, an output image representing the document having the content data based upon the content data on the document in each frame of the at least one frame, responsive to validating the document using the risk score.