Recognition-based Segmentation of Arabic Handwriting

Ashraf Elnagar, Rahima Bentrcia

2009

Abstract

Several segmentation approaches proposed in the past decades for Arabic handwritings suffer from over-segmentation. This problem decomposes a single letter into small strokes. The aim of this work is to handle this problem using Artificial Neural Networks with a set of combination rules to keep the correct strokes (letters) and combine the over-segmented ones to intact letters in a correct way. After word segmentation, the resulting segments are normalized. Then, a set of features was extracted from each segment and passed to Artificial Neural Network to be recognized. Finally, proposed combination rules were applied to unrecognized strokes and to specific recognized letters. The success rate of the experimental results exceeds 95%.

References

  1. M. Cheriet, N. Kharma and C-Lin Lui, C. Y.Suen, Character Recognition Systems: A Guide for Students and Practioners, John Wiley & Sons, Inc., 2007.
  2. R. Bentrecia and A. Elnagar, Handwriting Segmentation of Arabic Text, International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA 2008), Innsbruck, Austria, Pages: 122-127, Feb. 13-15, 2008.
  3. B. Al-Badr and S.A. Mahmoud, Survey and Bibliography of Arabic Optical Text Recognition, Signal Processing, vol. 41, pp. 49-77, 1995.
  4. A. Amin, Offline Arabic Character Recognition: The State of the Art, Pattern Recognition, vol. 31, pp. 517-530, 1998.
  5. A.S. Eldin and A.S. Nouh, Arabic Character Recognition: A Survey, Proc. SPIE Conf. Optical Pattern Recognition, pp. 331-340, 1998.
  6. M.S. Khorsheed, Off-Line Arabic Character Recognition: A Review, Pattern Analysis and Applications, vol. 5, pp. 31-45, 2002.
  7. B. Parhami and M. Taraghi, Automatic Recognition of Printed Farsi Texts, Pattern Recognition, vol. 14, pp. 395-403, 1981.
  8. A. Amin and G. Masini, Machine Recognition of Multi-Font Printed Arabic Texts, Proc. Int'l Conf. Pattern Recognition, pp. 392-395, 1986.
  9. A. Gillies, E. Erlandson, J. Trenkle, and S. Schlosser, Arabic Text Recognition System, In Proceedings of the Symposium on Document Image Understanding Technology, Annapolis, Maryland, 1999.
  10. L. Hamami and D. Berkani, Recognition System for Printed Multi-font and Multi-size Arabic Characters, The Arabian J. Science and Eng., vol. 27, pp. 57-72, 2002.
  11. M. Dehghan, K. Faez, M. Ahmadi, and M. Shridhar, Handwritten Farsi (Arabic) Word Recognition: A Holistic Approach Using Discrete HMM, Pattern Recognition, 34(5):1057- 1065, May 2001.
  12. S.A. Al-Qahtani and M.S. Khorsheed, An Omni-Font HTK-Based Arabic Recognition System, Proc. Eighth IASTED Int'l Conf. Artificial Intelligence and Soft Computing, 2004.
  13. S.A. Al-Qahtani and M.S. Khorsheed, A HTK-Based System to Recognize Arabic Script, Proc. Fourth IASTED Int'l Conf. Visualization, Imaging, and Image Processing, 2004.
  14. B. Al-Badr and R. Haralick, A Segmentation-Free Approach to Text Recognition with Application to Arabic Text, Int'l J. Document Analysis and Recognition, vol. 1, pp. 147- 166, 1998.
  15. B. Al-Badr and R. Haralick, Segmentation-Free Word Recognition with Application to Arabic, Proc. Int'l Conf. Document Analysis and Recognition, pp. 355-359, 1995.
  16. M.S. Khorsheed and W.F. Clocksin, Structural Features of Cursive Arabic Script, Proc. British Machine Vision Conf., pp. 422-431, 1999.
  17. A. Amin, Recognition of Printed Arabic Text Based on Global Features and Decision Tree Learning Techniques, Pattern Recognition, 33(8):1309-1323, August, 2000.
  18. M. Pechwitz and V. Maergner, HMM-Based Approach for Handwritten Arabic Word Recognition Using the IFN/ENIT-Database, In ICDAR IEEE Computer Society, pp. 890- 894, 2003.
  19. R. C. Gonzalez and P. Wintz, Digital Image Processing, 2nd edition. Boston, Massachusetts: Addison-Wesley, 1987.
  20. Jan Teuber, Digital Image Processing, Prentice Hall International Series in Acoustics, Speech and Signal Processing, 1991.
  21. P. Adibi, Farsi Handwritten Word Recognition Using a Continuous-Density VariableDuration Hidden Markov Model, Master of Science Thesis, Computer Engineering Department, Amir Kabir University of Technology, Tahran, Iran, 2001.
  22. R. Safabakhsh and P. Adibi, Nastaaligh Handwritten Word Recognition Using a Continuous-Density Variable-Duration HMM, The Arabian Journal for Science and Engineering, Volume 30, Number 1B, 2004.
Download


Paper Citation


in Harvard Style

Elnagar A. and Bentrcia R. (2009). Recognition-based Segmentation of Arabic Handwriting . In Proceedings of the 9th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2009) ISBN 978-989-8111-89-0, pages 83-92. DOI: 10.5220/0002179400830092


in Bibtex Style

@conference{pris09,
author={Ashraf Elnagar and Rahima Bentrcia},
title={Recognition-based Segmentation of Arabic Handwriting},
booktitle={Proceedings of the 9th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2009)},
year={2009},
pages={83-92},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002179400830092},
isbn={978-989-8111-89-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2009)
TI - Recognition-based Segmentation of Arabic Handwriting
SN - 978-989-8111-89-0
AU - Elnagar A.
AU - Bentrcia R.
PY - 2009
SP - 83
EP - 92
DO - 10.5220/0002179400830092