Machine Printed Arabic Character Recognition Using S-GCM

Author

Zheng, Liying

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Eng. Univ.

Volume

2

fYear

0

fDate

0-0 0

Firstpage

893

Lastpage

896

Abstract

Arabic characters are widely used in Arabic countries. However, there is a little work has been done on recognition of Arabic characters. This paper proposed a new method for recognition machine printed Arabic characters. The proposed method employs Ishii et al´s chaotic neural network model, which is called globally coupled map using the symmetric map (S-GCM), for recognizing Arabic characters. The proposed method is tested on two fonts, Simplified Arabic and Arabic Transparent, and 9 sizes, 8, 9, 10, 11, 12, 14, 16, 18, 20. The recognition rate is greater than 97%

Keywords

character recognition; character sets; image recognition; natural languages; neural nets; Arabic Transparent; Simplified Arabic; chaotic neural network model; globally coupled map using the symmetric map; machine printed Arabic character recognition; Artificial neural networks; Cellular neural networks; Chaos; Character recognition; Classification tree analysis; Computer science; Natural languages; Neural networks; Testing; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.779

Filename

1699349