Off-line Recognition of Handwritten Arabic Words Using Multiple Hidden Markov Models

  • Somaya Alma’adeed
  • Colin Higgins
  • Dave Elliman


Hidden Markov Models (HMM) have been used with some success in recognising printed Arabic words. In this paper, a complete scheme for unconstrained Arabic handwritten word recognition based on a Multiple discriminant Hidden Markov Models is presented and discussed. The overall engine of this combination of a global feature scheme with an HMM module, is a system able to classify Arabic-Handwritten words and has been tested on one hundred different writers. The system first attempts to remove some of the variation in the images that do not affect the identity of the handwritten word. Next, the system codes the skeleton and edge of the word such that feature information about the strokes in the skeleton is extracted. Then, a classification process based on a rule based classifier is used as that a global recognition engine to classify words into eight groups. Finally, for each group, the HMM approach is used for trial classification. The output is a word in the lexicon. A detailed experiment has been carried out, and successful recognition results are reported.


Hide Markov Model Recognition Rate Word Image Arabic Word Handwritten Word 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abuhaiba, S. Mahmoud, and R. Green, Recognition of Handwritten Cursive Arabic Characters, IEEE Trans. Pattern Analysis and Machine Intelligence, June, 1994, 16(6):664–672CrossRefGoogle Scholar
  2. 2.
    H. Alrnuallim and S. Yamaguchi, A method of recognition of Arabic cursive handwriting,, IEEE Trans. Pattern Anal. Machine Intell., 1987, TPAMI(9):715–722.CrossRefGoogle Scholar
  3. 3.
    S. Saadallah and S. Yacu, Design of an Arabic character reading machine, Proc. Of computer Processing of Arabic language, Kuwait, 1985.Google Scholar
  4. 4.
    Amin, H. Al-Sadoun and S. Fischer, Hand printed character recognition system using artificial network, Pattern recognition, 1996,29(4):663–675.CrossRefGoogle Scholar
  5. 5.
    A.M. Obaid, Arabic handwritten character recognition by neural nets, Journal on communications,,July-Aug, 1994, 45(i):90–91.Google Scholar
  6. 6.
    A. Saleh, A method of coding Arabic characters and it’s application to context free grammar, Pattern recognition letters, 1994, 15(12)1265–1271.CrossRefGoogle Scholar
  7. 7.
    S. Almaadeed, C. Higgens, and D. Elliman, A New Preprocessing System for the Recognition of Off-line Handwritten Arabic Words, IEEE International Symposium on Signal Processing and Information Technology, December, 2001.Google Scholar
  8. 8.
    S. Almaadeed, C. Higgens, and D. Ellirnan, a Database for Arabic Handwritten Text Recognition Research, Proc. 8th IWFHR, Ontario, Canada, 2000, (8): 130–135.Google Scholar
  9. 9.
    D. Guillevic and C. Y. Suen, Recognition of Legal Amount on Bank Cheques, Pattern Analysis & Applic, 1998, 1(1):485–489.CrossRefGoogle Scholar
  10. 10.
    Somaya Alma’adeed, Colin Higgins, and Dave Elliman, Recognition of OffLine Handwritten Arabic Words Using Hidden Marcov Model Approach, ICPR2002, Quebec City, August 2002.Google Scholar
  11. 11.
    Pavel Pudil, Petr Sornol, and Josef Kittler, Feature Selection in Statistical Pattern Recognition, ICPR 2002 Tutorial, Quebec City, August 2002.Google Scholar
  12. 12.
    Y. Al-Ohali, M. Cheriet and C. Y. Suen, Databases for Recognition of Handwritten Arabic Cheques, Proc. 7th IWFHR, Amsterdam, the Netherlands, 2000, (7):601–606.Google Scholar
  13. 13.
    M. Dehghan, K. Faez, M. Ahmadi, M. Shridhar, Handwritten Farsi word recognition: a holistic approach using discrete HMMM, Pattern Recognition, 2001,34(5):1057–1065.MATHCrossRefGoogle Scholar
  14. 14.
    S. Snoussi Maddouri, H. Arniri, Combination of Local and Global Vision Modelling for Arabic Handwritten Words Recognition, Proc. 8th IWFHR, Ontario, Canada, the Netherlands, 2000, 130–135.Google Scholar
  15. 15.
    M. Khorsheed, A dissertation for the degree of Doctor of philosophy, University of Cambridge, UK, 2002.Google Scholar

Copyright information

© Springer-Verlag London 2004

Authors and Affiliations

  • Somaya Alma’adeed
    • 1
  • Colin Higgins
    • 1
  • Dave Elliman
    • 1
  1. 1.University of NottinghamNottinghamUK

Personalised recommendations