A NEW SYNTHESIZING METHOD FOR HANDWRITING KOREAN SCRIPTS

Authors
Citation
Dh. Lee et Hg. Cho, A NEW SYNTHESIZING METHOD FOR HANDWRITING KOREAN SCRIPTS, International journal of pattern recognition and artificial intelligence, 12(1), 1998, pp. 45-61
Citations number
16
Categorie Soggetti
Computer Science Artificial Intelligence","Computer Science Artificial Intelligence
ISSN journal
02180014
Volume
12
Issue
1
Year of publication
1998
Pages
45 - 61
Database
ISI
SICI code
0218-0014(1998)12:1<45:ANSMFH>2.0.ZU;2-K
Abstract
So far there have been models for generating handwriting scripts of we stern languages. Since the basic structure of oriental languages such as Chinese, Japanese and Korean, is quite different from that of alpha bet-based western languages, western handwriting models cannot be appl ied directly to oriental languages except for a few models. In this pa per, we propose a new generation model for generating Korean handwriti ng scripts. For this we choose 11 characteristic parameters which dete rmine the shape of handwriting scripts. These parameters were selected experimentally by investigating ample Korean scripts. Furthermore we propose the Beta-velocity model to simulate the cursive stroke movemen t by manipulating curvilinear and cursive connection for consecutive s trokes within a letter or a word. In order to generate these oriental cursive strokes, we adopted Beta distribution curve basis which enable s one to make easy asymmetric velocity profile. By combining all these features, we synthesize various handwriting Korean scripts by control ling 11 characteristic parameters. In the final section of this paper, we give experimental results. These easy-to-synthesize Korean scripts can be used in evaluating off-line character recognition system and a word processor by supporting handwriting-style fonts.