Segmentation of connected Arabic characters using hidden Markov models

Author

Gouda, Alaa M. ; Rashwan, M.A.

Author_Institution

Dept. of Electr. & Comput. Eng., King Abdulaziz Univ., Jeddah, Saudi Arabia

fYear

2004

fDate

14-16 July 2004

Firstpage

115

Lastpage

119

Abstract

Because the Arabic text is connected by nature, segmentation of Arabic text into characters is a very important task for building an Arabic OCR. Although a lot of work has been done in this area, there is no perfect technique for segmentation has been used until now. In this paper, discrete hidden Markov models are used for segmentation of Arabic words into letters. The results are very encouraging. A system has been built and used for testing the proposed algorithm and the segmentation results achieved 99%.

Keywords

finite state machines; hidden Markov models; natural languages; optical character recognition; pattern classification; word processing; Arabic OCR; Arabic text; Arabic words; HMM; connected Arabic character segmentation; cursive script; discrete hidden Markov models; Character recognition; Hidden Markov models; Histograms; Neural networks; Optical character recognition software; Reconstruction algorithms; Text recognition; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence for Measurement Systems and Applications, 2004. CIMSA. 2004 IEEE International Conference on

Print_ISBN

0-7803-8341-9

Type

conf

DOI

10.1109/CIMSA.2004.1397244

Filename

1397244

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2609540