ONLINE RECOGNITION OF CURSIVE KOREAN CHARACTERS USING A SET OF EXTENDED PRIMITIVE STROKES AND FUZZY FUNCTIONS

Authors
KIM HJ KIM PK
Citation
Hj. Kim et Pk. Kim, ONLINE RECOGNITION OF CURSIVE KOREAN CHARACTERS USING A SET OF EXTENDED PRIMITIVE STROKES AND FUZZY FUNCTIONS, Pattern recognition letters, 17(1), 1996, pp. 19-28
Citations number
12
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence
Journal title
Pattern recognition letters → ACNP
ISSN journal
01678655
Volume
17
Issue
1
Year of publication
1996
Pages
19 - 28
Database
ISI
SICI code
0167-8655(1996)17:1<19:OROCKC>2.0.ZU;2-L
Abstract
We propose an efficient method for on-line recognition of cursive Kore an characters. The method uses a set of extended primitive strokes and fuzzy membership functions to extract cursive strokes. Positional rel ation of two strokes is computed also using fuzzy functions. With a se quence of stroke vectors and their positional relations computed, the method searches the target character on a character database. A test w ith 17,500 handwritten characters shows recognition rate of 96.3% with speed of 0.3 second per character.