A handwritten Chinese character recognition system based on neural-fuzzy theory

Author

Yang, Hsin-Tai ; Lin, Jue-Wen ; Lee, Shie-Jue

Author_Institution

Dept. of Electr. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan

Volume

2

fYear

1997

fDate

12-15 Oct 1997

Firstpage

1492

Abstract

In this paper, we propose a stroke-based handwritten Chinese character recognition system, based on neural networks and fuzzy set theory. Our system consists of three main modules that perform stroke extraction, feature extraction, and recognition, respectively. With the introduction of neural net technique and fuzzy set theory, the capability of tolerating transitional and rotational displacements is obtained. The system has been successfully implemented. Two kinds of experiments on similar Chinese characters have been done. One is based on 15 Chinese characters with the same radical. The average recognition rate in this experiment is 97%. The other is based on 23 similar Chinese characters. With 40 training samples for each character, a 91% recognition rate is achieved

Keywords

feature extraction; fuzzy set theory; neural nets; optical character recognition; feature extraction; fuzzy set theory; neural-fuzzy theory; rotation invariance; stroke extraction; stroke-based handwritten Chinese character recognition system; transition invariance; Character recognition; Feature extraction; Fuzzy set theory; Handwriting recognition; IEEE online publications; Natural languages; Neural networks; Office automation; Phase noise; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on

Conference_Location

Orlando, FL

ISSN

1062-922X

Print_ISBN

0-7803-4053-1

Type

conf

DOI

10.1109/ICSMC.1997.638200

Filename

638200