Using Contour-Direction Features to Speed Up Character Recognition

Frank Y. Shih; Pai Hsien Hsu

Using Contour-Direction Features to Speed Up Character Recognition

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Volume 2
Editors	P.P. Wang, P.P. Wang
Pages	200-203
Number of pages	4
Edition	2
State	Published - 2000
Event	Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000 - Atlantic City, NJ, United States Duration: Feb 27 2000 → Mar 3 2000

Publication series

Name	Proceedings of the Joint Conference on Information Sciences
Number	2
Volume	5

Other

Other	Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000
Country/Territory	United States
City	Atlantic City, NJ
Period	2/27/00 → 3/3/00

All Science Journal Classification (ASJC) codes

General Computer Science

Cite this

@inproceedings{ca362da59fdd4bc78d457226804e876f,

title = "Using Contour-Direction Features to Speed Up Character Recognition",

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.",

author = "Shih, {Frank Y.} and Hsu, {Pai Hsien}",

year = "2000",

language = "English (US)",

isbn = "0964345692",

series = "Proceedings of the Joint Conference on Information Sciences",

number = "2",

pages = "200--203",

editor = "P.P. Wang and P.P. Wang",

booktitle = "Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Volume 2",

edition = "2",

}

Shih, FY & Hsu, PH 2000, Using Contour-Direction Features to Speed Up Character Recognition. in PP Wang & PP Wang (eds), Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Volume 2. 2 edn, Proceedings of the Joint Conference on Information Sciences, no. 2, vol. 5, pp. 200-203, Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Atlantic City, NJ, United States, 2/27/00.

Using Contour-Direction Features to Speed Up Character Recognition. / Shih, Frank Y.; Hsu, Pai Hsien.
Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Volume 2. ed. / P.P. Wang; P.P. Wang. 2. ed. 2000. p. 200-203 (Proceedings of the Joint Conference on Information Sciences; Vol. 5, No. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Using Contour-Direction Features to Speed Up Character Recognition

AU - Shih, Frank Y.

AU - Hsu, Pai Hsien

PY - 2000

Y1 - 2000

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=1642354922&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642354922&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:1642354922

SN - 0964345692

SN - 9780964345690

T3 - Proceedings of the Joint Conference on Information Sciences

SP - 200

EP - 203

BT - Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000, Volume 2

A2 - Wang, P.P.

T2 - Proceedings of the Fifth Joint Conference on Information Sciences, JCIS 2000

Y2 - 27 February 2000 through 3 March 2000

ER -

Using Contour-Direction Features to Speed Up Character Recognition

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this