A BAYESIAN NEURAL-NETWORK FOR SEPARATING SIMILAR COMPLEX HANDWRITTEN CHINESE CHARACTERS

被引：3

作者：

CHANG, HD

WANG, JF

KUO, SC

机构：

[1] NATL CHENG KUNG UNIV,INST INFORMAT ENGN,1 UNIV RD,TAINAN 701,TAIWAN

[2] NATL CHENG KUNG UNIV,DEPT ELECT ENGN,TAINAN 701,TAIWAN

来源：

PATTERN RECOGNITION LETTERS | 1994年 / 15卷 / 04期

关键词：

HANDWRITTEN CHINESE CHARACTER; NEURAL NETWORK; SHAPE CODING; RECOGNITION;

D O I：

10.1016/0167-8655(94)90089-2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A Bayesian neural network for separating characters with the same number of linear like strokes and cross-points is proposed. It is trained by an incremental learning vector quantization algorithm which endows this system with incremental learning ability.

引用

页码：403 / 408

页数：6