CHINESE CHARACTER CLASSIFICATION USING AN ADAPTIVE RESONANCE NETWORK

被引：23

作者：

GAN, KW

LUA, KT

机构：

来源：

PATTERN RECOGNITION | 1992年 / 25卷 / 08期

关键词：

CHINESE CHARACTER CLASSIFICATION; ARTIFICIAL NEURAL NETWORK; ADAPTIVE RESONANCE THEORY; UNSUPERVISED LEARNING;

D O I：

10.1016/0031-3203(92)90040-P

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The ability to see through noise and distortion to a pattern is vital to the task of character recognition. Artificial neural networks exhibit such a capability as they are able to generalize automatically once they are trained. An application of an artificial neural network model, the Adaptive Resonance Theory (ART), to Chinese character classification is described. The ART classifier is used to classify 3755 Chinese characters. Our experimental results indicate that the classifier is able to achieve a high classification rate.

引用

页码：877 / 882

页数：6

共 9 条

[1]

ANDERBERG MR, 1973, CLUSTER ANAL APPLICA

[2]

[Anonymous], 1987, LEARNING INTERNAL RE

[3] ART-2 - SELF-ORGANIZATION OF STABLE CATEGORY RECOGNITION CODES FOR ANALOG INPUT PATTERNS [J].