Advertisement

On-line Arabic Handwritten Word Recognition Based on HMM and Combination of On-line and Off-line Features

  • Sherif Abdelazeem
  • Hesham M. Eraqi
  • Hany Ahmed

Abstract

Unconstrained handwritten text recognition is one of the most difficult problems in the field of pattern recognition. This paper presents a new on-line Arabic handwriting recognition system based on hidden Markov models (HMMs). Besides the common use of the off-line features for the HMM-based Arabic recognition systems, we add the use of on-line features and combination of the two approaches. The delta and acceleration features are used as approximations to the derivatives of the observation vectors with respect to time, and they have proved to be very effective in improving the system’s performance. Delayed strokes are a well-known problem in on-line handwriting recognition due to its varying writing order among different writers. We solved this problem by removing those delayed strokes by using a new delayed strokes detection approach that makes use of the baseline information and the shape of the strokes. The baseline detection method used in our system is based on horizontal projection. Removing delayed strokes has also led to the ability to combine some of the Arabic characters that share the same primary stroke and are only distinguishable by their delayed strokes into one class (HMM model), which increased the recognition rate. A new algorithm for lexicon reduction based on the detection of the delayed strokes has been developed. The lexicon reduction algorithm is used to improve the system’s performance in terms of speed and recognition rate. The on-line database ADAB of Tunisian town names is used for system training and evaluation. We achieved recognition rates up to 97.5 %, which is very promising compared to the highest recognition rate achieved on this database and is significantly higher than the recognition rates achieved by the other HMM-based Arabic handwriting recognition systems.

Keywords

Hide Markov Model Recognition Rate Test Word Handwriting Recognition High Recognition Rate 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Al-Habian, G., Assaleh, K.: Online Arabic handwriting recognition using continuous Gaussian mixture HMMs. In: Conference on International Intelligent and Advanced Systems (ICIAS), pp. 1183–1186 (2007) CrossRefGoogle Scholar
  2. 2.
    Al-Shatnawi, A., Omar, K.: Methods of Arabic language baseline detection—the state of art. Int. J. Comput. Sci. Netw. Secur. 8(10), 137–143 (2008) Google Scholar
  3. 3.
    Dolfing, J.G.A., Haeb-Umbach, R.: Signal representation for hidden Markov model based on-line handwriting recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 4, pp. 3385–3388 (1997) Google Scholar
  4. 4.
    El Abed, H., Kherallah, M., Märgner, V., Alimi, A.M.: Arabic online handwriting recognition competition—ADAB database and participating systems. Int. J. Doc. Anal. Recognit. 14(1), 15–23 (2011). Special Issue on Performance Evaluation CrossRefGoogle Scholar
  5. 5.
    Elanwar, R.I., Rashwan, M.A., Mashali, S.A.: Simultaneous segmentation and recognition of Arabic characters in an unconstrained on-line cursive handwritten document. In: World Academy of Science, Engineering and Technology, vol. 29 (2007) Google Scholar
  6. 6.
    Gonzales, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Addison-Wesley, Reading (2002) Google Scholar
  7. 7.
    Guillevic, D., Nishiwaki, D., Yamada, K.: Word lexicon reduction by character spotting. In: Proc. 7th International Workshop on Frontiers in Handwriting Recognition, pp. 373–382 (2000) Google Scholar
  8. 8.
    Guyon, I., Albrecht, P., Le Cun, Y., Denker, J., Hubbard, W.: Design of a neural network character recognizer for a touch terminal. Pattern Recognit. 24(2), 105–119 (1991) CrossRefGoogle Scholar
  9. 9.
    HTK Speech Recognition Toolkit. http://htk.eng.cam.ac.uk/
  10. 10.
    Khorsheed, M.S.: Off-line Arabic character recognition—a review. PAA Pattern Anal. Appl. 5, 31–45 (2002) MathSciNetCrossRefGoogle Scholar
  11. 11.
    Linde, Y., Buzo, A., Gray, R.M.: An algorithm for vector quantization design. IEEE Trans. Commun. 28, 48–95 (1980) CrossRefGoogle Scholar
  12. 12.
    Liu, C., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognit. 36, 2271–2285 (2003) MATHCrossRefGoogle Scholar
  13. 13.
    Märgner, V., El Abed, H.: ICDAR 2009 Arabic handwriting recognition competition. In: 10th International Conference on Document Analysis and Recognition (2009) Google Scholar
  14. 14.
    Pastor, M., Toselli, A., Vidal, E.: Writing speed normalization for on-line handwritten text recognition. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR) (2005) Google Scholar
  15. 15.
    Pechwitz, M., Märgner, V.: Baseline estimation for Arabic handwritten words. In: 8th Inter. Workshop on Frontiers in Handwriting Recognition (IWFHR’02), pp. 479–484 (2002) CrossRefGoogle Scholar
  16. 16.
    Rabiner, L., Juang, B.H.: Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs (1993) Google Scholar
  17. 17.
    Schenkel, M.E.: Handwriting recognition using neural networks and hidden Markov models. In: Series in Microelectronics, vol. 45 (1995) Google Scholar
  18. 18.
    Tanaka, H., Nakajima, K., Ishigaki, K., Akiyama, K., Nakagawa, M.: Hybrid pen-input character recognition system based on integration of on-line-offline recognition. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition (ICDAR), pp. 209–212 (1999) Google Scholar
  19. 19.
    Wagner, R.A., Fischer, M.J.: The string-to-string correction problem. J. ACM 21(1), 168–173 (1974) MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2012

Authors and Affiliations

  • Sherif Abdelazeem
    • 1
  • Hesham M. Eraqi
    • 1
  • Hany Ahmed
    • 1
  1. 1.Electronics Engineering Dept.The American University in Cairo (AUC)CairoEgypt

Personalised recommendations