OFF-LINE, HANDWRITTEN NUMERAL RECOGNITION BY PERTURBATION METHOD

Authors
HA TM BUNKE H
Citation
Tm. Ha et H. Bunke, OFF-LINE, HANDWRITTEN NUMERAL RECOGNITION BY PERTURBATION METHOD, IEEE transactions on pattern analysis and machine intelligence, 19(5), 1997, pp. 535-539
Citations number
18
Categorie Soggetti
Computer Sciences","Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on pattern analysis and machine intelligence → ACNP
ISSN journal
01628828
Volume
19
Issue
5
Year of publication
1997
Pages
535 - 539
Database
ISI
SICI code
0162-8828(1997)19:5<535:OHNRBP>2.0.ZU;2-F
Abstract
This paper presents a new approach to off-line, handwritten numeral re cognition. From the concept of perturbation due to writing habits and instruments, we propose a recognition method which is able to account for a variety of distortions due to eccentric handwriting. We tested o ur method on two worldwide standard databases of isolated numerals, na mely, CEDAR and NIST, and obtained 99.09 percent and 99.54 percent cor rect recognition rates al no-rejection level, respectively. The latter result was obtained by testing on more than 170,000 numerals.