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

Authors
CHANG HD WANG JF KUO SC
Citation
Hd. Chang et al., A BAYESIAN NEURAL-NETWORK FOR SEPARATING SIMILAR COMPLEX HANDWRITTEN CHINESE CHARACTERS, Pattern recognition letters, 15(4), 1994, pp. 403-408
Citations number
4
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence
Journal title
Pattern recognition letters → ACNP
ISSN journal
01678655
Volume
15
Issue
4
Year of publication
1994
Pages
403 - 408
Database
ISI
SICI code
0167-8655(1994)15:4<403:ABNFSS>2.0.ZU;2-R
Abstract
A Bayesian neural network for separating characters with the same numb er 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.