Using Contour-Direction Features to Speed Up Character Recognition

Frank Y. Shih, Pai Hsien Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we apply the modified contour-direction features to speed up the recognition process of English characters. Since there are only twenty-six letters in English characters, the candidate-cluster selection stage in training is skipped. We then apply the modified branch-and-bound algorithm in the detail-matching module. Experimental results show that we can achieve almost 100% recognition rate with the slight effect from varying the character image sizes.

Original languageEnglish (US)
Title of host publicationProceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Volume 2
EditorsP.P. Wang, P.P. Wang
Pages200-203
Number of pages4
Edition2
StatePublished - 2000
EventProceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000 - Atlantic City, NJ, United States
Duration: Feb 27 2000Mar 3 2000

Publication series

NameProceedings of the Joint Conference on Information Sciences
Number2
Volume5

Other

OtherProceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000
CountryUnited States
CityAtlantic City, NJ
Period2/27/003/3/00

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Using Contour-Direction Features to Speed Up Character Recognition'. Together they form a unique fingerprint.

Cite this