Off-line Arabic/Farsi handwritten word recognition using RBF neural network and genetic algorithm

Author

Bahmani, Zahra ; Alamdar, Fatemh ; Azmi, Reza ; Haratizadeh, Saman

Author_Institution

Comput. Dept., Alzahra Univ., Tehran, Iran

Volume

3

fYear

2010

fDate

29-31 Oct. 2010

Firstpage

352

Lastpage

357

Abstract

In this paper an off-line Arabic/Farsi handwritten recognition Algorithm on a subset of Farsi name is proposed. In this system, There is no sub-word segmentation phase. Script database includes 3300 images of 30 Farsi common names. The features are wavelet coefficients extracted from smoothed word image profiles in four standard directions. The Centers of competitive layer of RBF neural network have been determined by combining GA and K_Means clustering algorithm. Weights of supervised layer has been trained by using LMS rule and the distances of feature vector of each sample to the centre of RBF network have been computed based on warping function. Experimental results show advantages of this method in field of handwriting recognition.

Keywords

document image processing; feature extraction; genetic algorithms; handwritten character recognition; image segmentation; pattern clustering; radial basis function networks; wavelet transforms; word processing; Arabic language; Farsi language; LMS rule; RBF neural network; feature extraction; feature vector; genetic algorithm; handwritten word recognition; k-means clustering algorithm; script database; warping function; wavelet coefficient; Artificial neural networks; Computer architecture; Discrete wavelet transforms; Farsi Handwritten recognition; K_Means algorithm; RBF neural network and wavelet transform; genetic algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computing and Intelligent Systems (ICIS), 2010 IEEE International Conference on

Conference_Location

Xiamen

Print_ISBN

978-1-4244-6582-8

Type

conf

DOI

10.1109/ICICISYS.2010.5658635

Filename

5658635