US 11,816,909 B2
Document clusterization using neural networks
Ivan Zagaynov, Dolgoprudniy (RU); and Stanislav Semenov, Moscow (RU)
Assigned to ABBYY Development Inc., Raleigh, NC (US)
Filed by ABBYY Development Inc., Dover, DE (US)
Filed on Aug. 9, 2021, as Appl. No. 17/397,440.
Claims priority of application No. 2021123315 (RU), filed on Aug. 4, 2021.
Prior Publication US 2023/0038097 A1, Feb. 9, 2023
Int. Cl. G06V 30/40 (2022.01); G06N 3/04 (2023.01); G06F 18/23 (2023.01); G06F 18/213 (2023.01); G06V 30/18 (2022.01); G06V 30/41 (2022.01)
CPC G06V 30/40 (2022.01) [G06F 18/213 (2023.01); G06F 18/23 (2023.01); G06N 3/04 (2013.01); G06V 30/18 (2022.01); G06V 30/41 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
detecting, by a processing device, a set of keypoints in an input image;
generating a set of keypoint vectors, wherein each keypoint vector of the set of keypoint vectors is associated with a corresponding keypoint of the set of keypoints;
extracting a feature map from the input image;
producing a combination of the set of keypoint vectors with the feature map;
transforming the combination into a set of keypoint mapping vectors according to a predefined mapping scheme;
estimating, based on the set of keypoint mapping vectors, a plurality of importance factors associated with the set of keypoints; and
classifying the input image based on the set of keypoints and the plurality of importance factors.