US 11,915,465 B2
Apparatus and methods for converting lineless tables into lined tables using generative adversarial networks
Mehrdad Jabbarzadeh Gangeh, Mountain View, CA (US); and Hamid Reza Motahari-Nezad, Los Altos, CA (US)
Filed by EYGS LLP, London (GB)
Filed on Aug. 21, 2019, as Appl. No. 16/546,938.
Prior Publication US 2021/0056429 A1, Feb. 25, 2021
Int. Cl. G06V 10/82 (2022.01); G06V 10/44 (2022.01); G06F 16/25 (2019.01); G06N 3/088 (2023.01); G06N 3/045 (2023.01); G06V 30/19 (2022.01); G06V 30/412 (2022.01); G06V 30/414 (2022.01)
CPC G06V 10/454 (2022.01) [G06F 16/258 (2019.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01); G06V 10/82 (2022.01); G06V 30/19173 (2022.01); G06V 30/412 (2022.01); G06V 30/414 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A processor-implemented method, comprising:
removing, using a mask, at least some lines from a first set of tables to generate a second set of tables;
calculating a quality metric via a discriminative algorithm included in a conditional generative adversarial network (cGAN) based on an initial table from the first set of tables;
training the cGAN, using the first set of tables and the second set of tables, to produce a trained cGAN, the quality metric being passed as an input to a generative algorithm of the cGAN during the training of the cGAN;
identifying, using the trained cGAN, a plurality of lines for overlaying onto a lineless table; and
overlaying the plurality of lines onto the lineless table to produce a lined table.