AN OPTIMAL LINE SEGMENT EXTRACTION ALGORITHM FOR ONLINE CHINESE CHARACTER-RECOGNITION USING DYNAMIC-PROGRAMMING

Authors
TSENG CC JUAN CJ CHANG HC LIN JF
Citation
Cc. Tseng et al., AN OPTIMAL LINE SEGMENT EXTRACTION ALGORITHM FOR ONLINE CHINESE CHARACTER-RECOGNITION USING DYNAMIC-PROGRAMMING, Pattern recognition letters, 19(10), 1998, pp. 953-961
Citations number
9
Categorie Soggetti
Computer Science Artificial Intelligence","Computer Science Artificial Intelligence
Journal title
Pattern recognition letters → ACNP
ISSN journal
01678655
Volume
19
Issue
10
Year of publication
1998
Pages
953 - 961
Database
ISI
SICI code
0167-8655(1998)19:10<953:AOLSEA>2.0.ZU;2-R
Abstract
In this paper, a dynamic programming algorithm which can extract the l ine segments from the loci of Chinese character in running hand or cur sive writing is proposed. This algorithm tries to find the minimum lin e segments to fit the cursive stroke of character within the prescribe d error bound. Three error measures are presented to construct a globa lly optimal approximation to the given stroke, including sum of deviat ion, peak deviation and length error. Extensive experiments are demons trated to illustrate the performance of the proposed algorithm. (C) 19 98 Elsevier Science B.V. All rights reserved.