A weighted competitive learning method extracting skeleton pattern from Japanese Kanji characters

Author

Nakayama, Kenji ; Kato, Takuo

Author_Institution

Dept. of Electr. & Comput. Eng., Kanazawa Univ., Japan

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4237

Abstract

A weighted competitive learning (WCL) method was proposed by authors for extracting skeleton patterns from digit and alphabet characters. The extracted pattern is essential in character recognition. It can satisfy the following important requirements. (a) Insensitive to irregular edge lines. (b) Nonstructure patterns are not extracted. (c) Insensitive to nonuniform line width. (d) Line information should be held even though the line width widely changes in a character. In this paper, the previous WCL method is improved for application to more complicated characters, such as Japanese Kanji characters. Furthermore, a PDP model, implements the WCL method, is provided

Keywords

character recognition; unsupervised learning; Japanese Kanji characters; character recognition; irregular edge line insensitivity; nonstructure patterns; nonuniform line width insensitivity; skeleton pattern extraction; weighted competitive learning method; Character recognition; Computer simulation; Data mining; Handwriting recognition; Learning systems; Neural networks; Pattern recognition; Signal analysis; Skeleton; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374946

Filename

374946