US 11,922,318 B2
System and method of character recognition using fully convolutional neural networks with attention
Felipe Petroski Such, Rochester, NY (US); Raymond Ptucha, Rochester, NY (US); Frank Brockler, Rochester, NY (US); and Paul Hutkowski, Rochester, NY (US)
Assigned to KODAK ALARIS, INC., Rochester, NY (US)
Filed by Kodak Alaris Inc., Rochester, NY (US)
Filed on Oct. 20, 2020, as Appl. No. 17/075,513.
Application 17/075,513 is a continuation of application No. 15/812,681, filed on Nov. 14, 2017, granted, now 10,846,523.
Application 15/812,681 is a continuation in part of application No. 15/708,918, filed on Sep. 19, 2017, abandoned.
Application 15/708,918 is a continuation in part of application No. 15/709,014, filed on Sep. 19, 2017, granted, now 10,936,862.
Claims priority of provisional application 62/524,983, filed on Jun. 26, 2017.
Claims priority of provisional application 62/422,000, filed on Nov. 14, 2016.
Prior Publication US 2021/0034850 A1, Feb. 4, 2021
Int. Cl. G06N 3/084 (2023.01); G06F 18/2413 (2023.01); G06F 40/242 (2020.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/146 (2022.01); G06V 30/18 (2022.01); G06V 30/32 (2022.01); G06V 30/414 (2022.01)
CPC G06N 3/084 (2013.01) [G06F 18/2413 (2023.01); G06F 40/242 (2020.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 30/1478 (2022.01); G06V 30/18057 (2022.01); G06V 30/347 (2022.01); G06V 30/36 (2022.01); G06V 30/414 (2022.01); G06V 30/10 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor of a computing device, cause the computing device to:
receive a digital image corresponding to a word block, the word block containing at least one symbol corresponding to a letter, number, character, or a combination thereof;
evaluate the word block with a first neural network, the first neural network assigning at least one of a descriptor or a steering factor to the word block as a first output;
process the word block with a second neural network, the second neural network evaluating the steering factor to prioritize evaluation;
combine the first output from the first neural network and a second output from the second neural network;
process an input with a third neural network, the output of which is combined with the first and second outputs;
wherein the input to the third neural network comprises an entire text block, an entire line of text, an entire paragraph, an entire entry field of a form, an entire document, or an entire batch of documents, and;
output a predicted word corresponding to a value of the word block.