US 12,014,561 B2
Image reading systems, methods and storage medium for performing geometric extraction
Soumitri Naga Kolavennu, Plymouth, MN (US); Ankur Tomar, Minneapolis, MN (US); Varshini Sriram, Minneapolis, MN (US); Rodolfo Carriedo Roque, Apple Valley, MN (US); Lavanya Basavaraju, Minneapolis, MN (US); and Bryan Lee Stuhlsatz, Merrifield, MN (US)
Assigned to U.S. Bank National Association, Minneapolis, MN (US)
Filed by U.S. Bank National Association, Minneapolis, MN (US)
Filed on Jan. 5, 2022, as Appl. No. 17/569,121.
Claims priority of provisional application 63/169,789, filed on Apr. 1, 2021.
Prior Publication US 2022/0319216 A1, Oct. 6, 2022
Int. Cl. G06V 30/414 (2022.01); G06V 10/50 (2022.01); G06V 10/778 (2022.01); G06V 30/18 (2022.01)
CPC G06V 30/414 (2022.01) [G06V 10/50 (2022.01); G06V 10/778 (2022.01); G06V 30/18086 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for processing a document having one or more pages, comprising:
receiving an unstructured document;
recognizing a plurality of textual blocks on at least a portion of a page of the unstructured document;
generating a plurality of bounding boxes, each bounding box surrounding and corresponding to one of the plurality of textual blocks and having coordinates of a plurality of vertices;
determining a plurality of search paths, each search path having coordinates of two endpoints and connecting at least two bounding boxes; and
generating a graph representation of the at least a portion of the page, the graph representation including the plurality of textual blocks, the coordinates of the plurality of vertices of each bounding box and the coordinates of the two endpoints of each search path.