IngentaConnect Arabic writer identification based on hybrid spectral-statistical...

Authors: Al-Dmour, Ayman¹; Zitar, Raed Abu²

Source: Journal of Experimental & Theoretical Artificial Intelligence, Volume 19, Number 4, December 2007 , pp. 307-332(26)

Publisher: Taylor and Francis Ltd

Abstract:

Many techniques have been reported for handwriting-based writer identification. None of these techniques assume that the written text is in Arabic. In this paper we present a new technique for feature extraction based on hybrid spectral-statistical measures (SSMs) of texture. We show its effectiveness compared with multiple-channel (Gabor) filters and the grey-level co-occurrence matrix (GLCM), which are well-known techniques yielding a high performance in writer identification in Roman handwriting. Texture features were extracted for wide range of frequency and orientation because of the nature of the spread of Arabic handwriting compared with Roman handwriting, and the most discriminant features were selected with a model for feature selection using hybrid support vector machine-genetic algorithm techniques. Four classification techniques were used: linear discriminant classifier (LDC), support vector machine (SVM), weighted Euclidean distance (WED), and the K nearest neighbours (K_NN) classifier. Experiments were performed using Arabic handwriting samples from 20 different people and very promising results of 90.0% correct identification were achieved.

Keywords: Writer identification; Texture analysis; Arabic handwriting; Power spectrum; Feature selection

Document Type: Research article

DOI: 10.1080/09528130701228800

Affiliations: 1: Arab Academy, College of Information Technology, Jordan 2: College of Information Technology, Philadelphia University, Jordan

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$40.89 plus tax

Arabic writer identification based on hybrid spectral-statistical measures