Invention Grant
- Patent Title: Active segmention of scanned images based on deep reinforcement learning for OCR applications
-
Application No.: US16004735Application Date: 2018-06-11
-
Publication No.: US10685261B2Publication Date: 2020-06-16
- Inventor: Xuewei Qi , Orhan Bulan , David H. Clifford , David J. Hiemenga , Yehenew G. Mengistu
- Applicant: GM Global Technology Operations LLC
- Applicant Address: US MI Detroit
- Assignee: GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Current Assignee: GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Current Assignee Address: US MI Detroit
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06T7/11 ; H04N1/028 ; G06K9/00

Abstract:
A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system uses a model and a reward/penalty function to guide the traversal through the array. The system changes direction when the data encountered while traversing the array in the selected direction represents one of the elements of the 2D array and continues in the selected direction when the data represents a joint between two elements of the 2D array. The system recognizes one or more of the elements of the 2D array segmented by traversing the array.
Public/Granted literature
- US20190377988A1 ACTIVE SEGMENTION OF SCANNED IMAGES BASED ON DEEP REINFORCEMENT LEARNING FOR OCR APPLICATIONS Public/Granted day:2019-12-12
Information query