![](/images/graphics-bg.png)
Neural networks and support vector machines classifiers for writer identification using Arabic script
Joint Authors
Source
The International Arab Journal of Information Technology
Issue
Vol. 5, Issue 1 (31 Jan. 2008), pp.92-101, 10 p.
Publisher
Publication Date
2008-01-31
Country of Publication
Jordan
No. of Pages
10
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
In this paper, we present an approach for writer identification carried out using off-line Arabic handwriting.
Our proposed method is based on the combination of global and structural features.
We used genetic algorithm for feature subset selection in order to eliminate the redundant and irrelevant ones.
A comparative evaluation between two classifiers is done using Support Vector Machines and Multilayer Perceptron (MLP).
The best results have been achieved using optimal feature subset and MLP with an average rate of 94%.
Experiments have been carried out on a database of 120 text samples.
The choice of the text samples was made to ensure the involvement of the various internal shapes and letter locations within asubword.
American Psychological Association (APA)
Gazzah, Sami& Bin Imarah, Najwa. 2008. Neural networks and support vector machines classifiers for writer identification using Arabic script. The International Arab Journal of Information Technology،Vol. 5, no. 1, pp.92-101.
https://search.emarefa.net/detail/BIM-10575
Modern Language Association (MLA)
Gazzah, Sami& Bin Imarah, Najwa. Neural networks and support vector machines classifiers for writer identification using Arabic script. The International Arab Journal of Information Technology Vol. 5, no. 1 (Jan. 2008), pp.92-101.
https://search.emarefa.net/detail/BIM-10575
American Medical Association (AMA)
Gazzah, Sami& Bin Imarah, Najwa. Neural networks and support vector machines classifiers for writer identification using Arabic script. The International Arab Journal of Information Technology. 2008. Vol. 5, no. 1, pp.92-101.
https://search.emarefa.net/detail/BIM-10575
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 99-100
Record ID
BIM-10575