Arabic Character Recognition based on Statistical Features - A Comparative Study

Mariem Gargouri Kchaou, Slim Kanoun, Fouad Slimane, Souhir Bouaziz Affes

Abstract

This paper presents a comparative study for Arabic optical character recognition techniques according to statistic approach. So, the current work consists in experimenting character image characterization and matching to show the most robust and reliable techniques. For features extraction phase, we test invariant moments, affine moment invariants, Tsirikolias–Mertzios moments, Zernike moments, Fourier-Mellin transform and Fourier descriptors. And for the classification phase, we use k-Nearest Neighbors and Support Vector Machine. Our data collection encloses 3 datasets. The first contains 2320 multi-font and multi-scale printed samples. The second contains 9280 multi-font, multi-scale and multi-oriented printed samples. And, the third contains 2900 handwritten samples which are extracted from the IFN/ENIT data. The aim was to cover a wide spectrum of Arabic characters complexity. The best performance rates found for each dataset are 99.91%, 99.26% and 66.68% respectively.

References

  1. Abandah, G. and Anssari, N., 2009. Novel moment features extraction for recognizing handwritten arabic letters. J. Comput. Sci., 5: 226-232. DOI: 10.3844/ jcssp. 2009. 226.232.
  2. Abdul Sattar, S., Shah, S., 2012. Character Recognition of Arabic Script Languages. ICCIT, pp. 502-506.
  3. Aboaisha, Hosain, Xu, Zhijie and El-Feghi, Idris (2012) An investigation on efficient feature extraction approaches for Arabic letter recognition. In: PQDJCEAR' Conference 2012: CEARC'12, pp. 80- 85. ISBN 978-1-86218-106-9.
  4. Arif, M., Brouard, T., Vincent, N., 2006. A new fuzzy kNearest Neighbors rule. Pattern recognition.
  5. Imran, K. P., Abdulbari A. A., Ramteke R. J., 2012. Recognition of Offline Handwritten Isolated Urdu Character. ACR ISSN: 0975-3273 & E-ISSN: 0975- 9085, Volume 4, Issue 1, pp.-117-121.
  6. Jenabzadeh, M. R., Azmi, R., Pishgoo, B., Shirazi, S.S., 2011. Two Methods for Recognition of Hand Written Farsi Characters. IJIP, Vol. 5(4).
  7. Mozaffari, S., Faez, K., Kanan, H., R., 2004. Feature Comparison between Fractal Codes and Wavelet Transform in Handwritten Alphanumeric Recognition Using SVM Classifier. ICPR (2): 331-334.
  8. Sabri A. Mahmoud, Ashraf S. Mahmoud, 2009. Arabic Character Recognition Using Modified Fourier Spectrum (MFS) vs. Fourier Descriptors. Cybernetics and Systems 40(3): 189-210.
  9. Slimane, F., Ingold, R., Kanoun, S., Alimi, M. A., and Hennebert, J., 2009. A New Arabic Printed Text Image Database and Evaluation Protocols. In proc. of 10th IEEE ICDAR 2009, Barcelona (Spain), July 26 - 29 2009 , pp. 946-950.
  10. Zaghloul, R. I., AlRawashdeh, E., F., Bader, D. M. K., 2011. Multilevel Classifier in Recognition of Handwritten Arabic Characters. Journal of Computer Science 7 (4): 512-518.
Download


Paper Citation


in Harvard Style

Gargouri Kchaou M., Kanoun S., Slimane F. and Bouaziz Affes S. (2013). Arabic Character Recognition based on Statistical Features - A Comparative Study . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 281-284. DOI: 10.5220/0004265602810284


in Bibtex Style

@conference{icpram13,
author={Mariem Gargouri Kchaou and Slim Kanoun and Fouad Slimane and Souhir Bouaziz Affes},
title={Arabic Character Recognition based on Statistical Features - A Comparative Study},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={281-284},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004265602810284},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Arabic Character Recognition based on Statistical Features - A Comparative Study
SN - 978-989-8565-41-9
AU - Gargouri Kchaou M.
AU - Kanoun S.
AU - Slimane F.
AU - Bouaziz Affes S.
PY - 2013
SP - 281
EP - 284
DO - 10.5220/0004265602810284