A neural network approach for Chinese character recognition
Journal
International Joint Conference on Neural Networks
Pages
II917-II923
Date Issued
1990
Author(s)
Pan, Chung-Chi
Abstract
A neural network model adapted from Fukushima's Neocognitron is applied to the pattern recognition of Chinese characters. Chinese characters are well known for their nonalphabetic and two-dimensional features. Chinese characters are viewed as two-dimensional patterns, and some simple subpatterns, called primitives, are identified for hierarchical processing in a neural network. Simulation results show the feasibility and the effectiveness of this approach
Description
San Diego, CA
Type
conference paper
File(s)![Thumbnail Image]()
Loading...
Name
00137810.pdf
Size
464.34 KB
Format
Adobe PDF
Checksum
(MD5):e327c3af7b9b15c94c5d8ee245a3a60f