An approach to offline Arabic character recognition using neural networks

Author

Nawaz, S.N. ; Sarfraz, M. ; Zidouri, A. ; Al-Khatib, W.G.

Author_Institution

King Fahd Univ. of Pet. & Miner., Dhahran, Saudi Arabia

Volume

3

fYear

2003

fDate

14-17 Dec. 2003

Firstpage

1328

Abstract

Character recognition system can contribute tremendously towards the advancement of automation process and can be useful in many other applications such as Data Entry, Check Verification etc. This paper presents a technique for the automatic recognition of Arabic Characters. The technique is based on Neural Pattern Recognition Approach. The main features of the system are preprocessing of the text, segmentation of the text to individual characters, Feature extraction using centralized moments technique and recognition using RBF Network. The system is implemented in Java Programming Language under Windows Environment. The System is designed for a single font multi size character set.

Keywords

feature extraction; handwritten character recognition; image denoising; image segmentation; learning (artificial intelligence); radial basis function networks; Java package; RBF network; automatic recognition; centralized moments technique; details-enhancement; feature extraction; neural networks; neural pattern recognition; noise removal; offline Arabic character recognition; segmentation; text preprocessing; vertical projection profile; Character recognition; Feature extraction; Image recognition; Image segmentation; Natural languages; Neural networks; Optical character recognition software; Pattern recognition; Pixel; Text recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits and Systems, 2003. ICECS 2003. Proceedings of the 2003 10th IEEE International Conference on

Print_ISBN

0-7803-8163-7

Type

conf

DOI

10.1109/ICECS.2003.1301760

Filename

1301760