Combining neural networks for Arabic handwriting recognition
Joint Authors
Leila, Chergui
Maamar, Kef
Salim, Chikhi
Source
The International Arab Journal of Information Technology
Issue
Vol. 9, Issue 6 (30 Nov. 2012)8 p.
Publisher
Publication Date
2012-11-30
Country of Publication
Jordan
No. of Pages
8
Main Subjects
Languages & Comparative Literature
Information Technology and Computer Science
Topics
Abstract EN
Combining classifiers is an approach that has been shown to be useful on numerous occasions when striving for further improvement over the performance of individual classifiers.
In this paper we present a Multiple Classifier System (MCS) for off-line Arabic handwriting recognition.
The MCS combines three neuronal recognition systems based on Fuzzy ART network used for the first time in Arabic OCR, multi-layer perceptron and radial basic functions.
We use various feature sets based on Tche biche, Hu and Zernike moments.
For deriving the final decision, different combining schemes are applied.
The best combination ensemble has a recognition rate of 90, 10 %, which is significantly higher than the 84, 31% achieved by the best individual classifier.
To demonstrate the high performance of the classification system, the results are compared with three research using IFN / ENIT database
American Psychological Association (APA)
Leila, Chergui& Maamar, Kef& Salim, Chikhi. 2012. Combining neural networks for Arabic handwriting recognition. The International Arab Journal of Information Technology،Vol. 9, no. 6.
https://search.emarefa.net/detail/BIM-305092
Modern Language Association (MLA)
Leila, Chergui…[et al.]. Combining neural networks for Arabic handwriting recognition. The International Arab Journal of Information Technology Vol. 9, no. 6 (Nov. 2012).
https://search.emarefa.net/detail/BIM-305092
American Medical Association (AMA)
Leila, Chergui& Maamar, Kef& Salim, Chikhi. Combining neural networks for Arabic handwriting recognition. The International Arab Journal of Information Technology. 2012. Vol. 9, no. 6.
https://search.emarefa.net/detail/BIM-305092
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references.
Record ID
BIM-305092