Invention Grant
- Patent Title: System and method of character recognition using fully convolutional neural networks with attention
-
Application No.: US17075511Application Date: 2020-10-20
-
Publication No.: US11715014B2Publication Date: 2023-08-01
- Inventor: Felipe Petroski Such , Raymond Ptucha , Frank Brockler , Paul Hutkowski
- Applicant: Kodak Alaris Inc.
- Applicant Address: US NY Rochester
- Assignee: KODAK ALARIS INC.
- Current Assignee: KODAK ALARIS INC.
- Current Assignee Address: US NY Rochester
- Agency: Hogan Lovells US LLP
- The original application number of the division: US15812681 2017.11.14
- Main IPC: G06N3/084
- IPC: G06N3/084 ; G06F40/242 ; G06V30/32 ; G06V30/414 ; G06V30/146 ; G06F18/2413 ; G06N3/044 ; G06N3/045 ; G06V30/18 ; G06V10/764 ; G06V10/82 ; G06V30/10

Abstract:
Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.
Public/Granted literature
- US20210034849A1 SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION Public/Granted day:2021-02-04
Information query