Synthizing Handwritten Arabic Text Using Active Shape Models

  • Laslo Dinges
  • Moftah Elzobi
  • Ayoub Al-Hamadi
  • Zaher Al Aghbari
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 102)


This research paper proposes a template based approach for generating an unlimited number of synthesized handwritten Arabic characters. It starts by generating a polygonal representation for each training sample for every character class. Then for each class an Active Shape Model (ASM) is used to unify all polygonal samples in one compact representation. Accordingly, any desired number of synthesized characters, can be produced, as a result of simple linear combination between the Eigenvalues and Eigenvectors of the ASM. Ultimately, the contour of synthesized character is smoothed using piecewise cubic hermit interpolation. Moreover, by combining multiple synthesized characters, our system is capable of producing synthesized Arabic words. Even though experiments have shown that a perfect human- like handwriting is still far away. We think that our approach is a very promising and a step forward towards achieving this goal.


Deformable Model Hermit Interpolation Handwriting Recognition Active Shape Model Arabic 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.
    Maegner, V., Abed, H.E.: Databases and competitions: strategies to improve Arabic recognition systems, pp. 82–103. Springer, Collage Park (2008)Google Scholar
  2. 2.
    Elarian, Y.S., Al-Muhsateb, H.A., Ghouti, L.M.: Arabic handwriting synthesis. In: First International Workshop on Frontiers in Arabic Handwriting Recognition (2011),
  3. 3.
    Guyon, I.: Handwriting synthesis from handwritten glyphs. In: Proceedings of the Fifth International Workshop on Frontiers of Handwriting Recognition, pp. 309–312 (1996)Google Scholar
  4. 4.
    Margner, V., Pechwitz, M.: Synthetic data for arabic ocr system development. In: Proceedings. Sixth International Conference on Document Analysis and Recognition, pp. 1159–1163 (2001)Google Scholar
  5. 5.
    Varga, T., Bunke, H.: Generation of synthetic training data for an hmm-based handwriting recognition system. In: Proceedings. Seventh International Conference on Document Analysis and Recognition, vol. (1), pp. 618–622 (2003)Google Scholar
  6. 6.
    Wang, J., Wu, C., Xu, Y.Q., Shum, H.Y.: Combining shape and physical models for on-line cursive handwriting synthesis (2003)Google Scholar
  7. 7.
    Rao, P.V.S.: Shape vectors: An efficient parametric representation for the synthesis and recognition of hand script characters (1993)Google Scholar
  8. 8.
    Miyao, H., Maruyama, M.: Virtual example synthesis based on pca for off-line handwritten character recognition. In: Document Analysis Systems, pp. 96–105 (2006)Google Scholar
  9. 9.
    Cheung, K.-W., Chin, R.T., Yeung, D.-Y., Chin, T.: A bayesian framework for deformable pattern recognition with application to handwritten character recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 1382–1388 (1998)CrossRefGoogle Scholar
  10. 10.
    Al-Zubi, S.: Active shape structural model. Technical report (2004)Google Scholar
  11. 11.
    Shi, D., Gunn, S.R., Damper, R.I.: Handwritten chinese radical recognition using nonlinear active shape models. IEEE Trans. Pattern Anal. Mach. Intell. 25(2), 277–280 (2003)CrossRefGoogle Scholar
  12. 12.
    Lam, L., Lee, S.W., Suen, C.Y.: Thinning methodologies-a comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 14, 869–885 (1992)CrossRefGoogle Scholar
  13. 13.
    Bradski, G., Kaehler, A.: Learning opencv (2008)Google Scholar
  14. 14.
    Bender, M., Brill, M.: Computergrafik - ein anwendungsorientiertes Lehrbuch, 2. auflage editions. Hanser Verlag (2006)Google Scholar
  15. 15.
    Jaklic, G., Kozak, J., Krajnc, M., Vitrih, V., Zagar, E.: Geometric lagrange interpolation by planar cubic pythagorean-hodograph curves. Comput. Aided Geom. Des. 25, 720–728 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  16. 16.
    Aghbari, Z.A., Brook, S.: Hah manuscripts: A holistic paradigm for classifying and retrieving historical arabic handwritten documents. Expert Syst. Appl. 36, 10942–10951 (2009)CrossRefGoogle Scholar
  17. 17.
    Lavrenko, V., Rath, T.M., Manmatha, R.: Holistic word recognition for handwritten historical documents. In: Proceedings of the First International Workshop on Document Image Analysis for Libraries (DIAL 2004), p. 278. IEEE Computer Society Press, Los Alamitos (2004)CrossRefGoogle Scholar
  18. 18.
    Biadsy, F., El-Sana, J., Habash, N.: Online arabic handwriting recognition using hidden markov models. In: Lorette, G. (ed.) Tenth International Workshop on Frontiers in Handwriting Recognition. Suvisoft (2006),
  19. 19.
    Aljuaid, H., Muhammad, Z., Sarfraz, M.: A tool to develop arabic handwriting recognition system using genetic approachGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Laslo Dinges
    • 1
  • Moftah Elzobi
    • 1
  • Ayoub Al-Hamadi
    • 1
  • Zaher Al Aghbari
    • 2
  1. 1.Institute for ElectronicsSignal Processing and Communications (IESK)Germany
  2. 2.Computer Science DepartmentUniversity of SharjahUAE

Personalised recommendations