US 12,333,839 B2
Neural network architecture for classifying documents
Dasaprakash Krishnamurthy, Chennai (IN); José Pablo Romero Valle, Salamanca (ES); and Álvaro Hernández Hernández, Salamanca (ES)
Assigned to UST Global (Singapore) Pte. Limited, Singapore (SG)
Filed by UST Global (Singapore) Pte. Limited, Singapore (SG)
Filed on Aug. 2, 2022, as Appl. No. 17/816,940.
Claims priority of application No. 202211022816 (IN), filed on Apr. 18, 2022.
Prior Publication US 2023/0334885 A1, Oct. 19, 2023
Int. Cl. G06V 30/00 (2022.01); G06V 10/82 (2022.01); G06V 30/14 (2022.01); G06V 30/148 (2022.01); G06V 30/19 (2022.01); G06V 30/41 (2022.01)
CPC G06V 30/19173 (2022.01) [G06V 10/82 (2022.01); G06V 30/1448 (2022.01); G06V 30/148 (2022.01); G06V 30/1918 (2022.01); G06V 30/41 (2022.01)] 10 Claims
OG exemplary drawing
 
1. A method of classifying a document, comprising:
receiving, from a storage device, an image of the document;
obtaining a predefined user configuration indicative of a term of interest for the document;
converting, by a document importer, the image to machine-readable data using Optical Character Recognition (OCR);
performing, by a first convolutional neural network, semantic enrichment by highlighting the term of interest in the image based on the machine-readable data;
splitting, by a second convolutional neural network, the image into four quadrants for identifying a positional context of the term of interest in the quadrants, wherein the first convolutional neural network and the second convolutional neural network are a ResNet-152 model;
generating a model representation for each of the quadrants;
concatenating the model representations of the quadrants; and
classifying the image based on the concatenated model representations.