Peripheral and global features for use in coarse classification of Chinese characters

Kuo Sen Chou, Kuo Chin Fan, Tzu I. Fan

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

In this paper, a simple and effective approach to the coarse classification of handwritten Chinese characters is proposed. In our approach, a Chinese character is characterized by string representation using periphery and global feature vectors. The peripheral features include four strings to represent the structure of segments in top, bottom, left, and right directions. The global features include the number of horizontal segments in the top direction and bottom direction, and the number of stroke segments in a character. In addition, a scoring-based coarse classification scheme is devised in choosing the proper candidate characters. Twenty sets of Chinese characters (5401 characters/set) are tested. The number of candidate characters is reduced from 5401 to about 80 with the error rate less than 1.2% in average. Experimental results reveal the feasibility of the proposed approach in classifying Chinese characters.

Original languageEnglish
Pages (from-to)483-489
Number of pages7
JournalPattern Recognition
Volume30
Issue number3
DOIs
StatePublished - Mar 1997

Keywords

  • Chinese character recognition
  • Coarse classification
  • Global feature
  • Peripheral feature

Fingerprint

Dive into the research topics of 'Peripheral and global features for use in coarse classification of Chinese characters'. Together they form a unique fingerprint.

Cite this