Off-Line Handwritten Arabic Word Recognition Using SVMs with Normalized Poly Kernel

  • Abdulrahman Alalshekmubarak
  • Amir Hussain
  • Qiu-Feng Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7664)


Handwriting recognition is a complicated process that many applications rely on, such as mail sorting, cheque processing, digitalisation and translation. The recognition of handwritten Arabic is still an ongoing challenge mainly due to the similarity among its letters and the variety of writing styles. In this paper, a novel approach is proposed that uses support vector machines (SVMs) with normalized poly kernel. The well-known Arabic handwritten database, IFN/ENIT-database, which contains 936 city names with more than 32,492 instances, is used to test the proposed system. The results of this novel approach are compared with the results of two different studies. The comparison shows that a higher accuracy rate is obtained using the proposed system.


SVM Offline word recognition Normalized poly kernel Feature extraction 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Farghaly, A., Shaalan, K.: Arabic Natural Language Processing: Challenges and Solutions, vol. 8, pp. 14:1–14:22 (2009)Google Scholar
  2. 2.
    Aburas, A.A., Rehiel, S.A.: Comprehensive Review for Arabic Handwriting and Printed Characters Recognition. In: Intell. Adv. Syst. ICIAS, pp. 730–735 (2007)Google Scholar
  3. 3.
    Aburas, A.A., Gumah, M.E.: Arabic Handwriting Recognition: Challenges and Solutions. In: International Symposium on Information Technology, pp. 1–6 (2008)Google Scholar
  4. 4.
    El Abed, H., Margner, V.: Comparison of Different Preprocessing and Feature Extraction Methods for Offline Recognition of Handwritten Arabic Words. In: 9th International Conference on Document Analysis and Recognition, pp. 974–978 (2007)Google Scholar
  5. 5.
    Genchi, H., Mori, K., Watanabe, S., Katsuragi, S.: Recognition of Handwritten Numerical Characters for Automatic Letter Sorting. Pro. IEEE 56, 1292–1301 (1968)CrossRefGoogle Scholar
  6. 6.
    Masterson, J.L., Hirsch, R.S.: Machine Recognition of Constrained Handwritten Arabic Numbers. IRE Transactions on Human Factors in Electronics HFE-3, 62–65 (1962)Google Scholar
  7. 7.
    Almuallim, H., Yamaguchi, S.: A method of recognition of Arabic cursive handwriting. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-9, 715–722 (1987)CrossRefGoogle Scholar
  8. 8.
    Margner, V., Abed, H.E.: Arabic Handwriting Recognition Competition. In: International Conference on Document Analysis and Recognition, ICDAR, pp. 1444–1448 (2011)Google Scholar
  9. 9.
    Cheriet, M., Kharma, M., Liu, C., Suen, C.: Character Recognition Systems: A Guide for Students and Practitioners. John Wiley & Sons, Inc., Hoboken (2007)zbMATHCrossRefGoogle Scholar
  10. 10.
    El Affar, A., Ferdous, K., El Fadili, H., Qjidaa, H.: Krawtchouk Moment Feature Extraction for Neural Arabic Handwritten Words Recognition. In: International Conference Multimedia Computing and Systems, pp. 443–448 (2009)Google Scholar
  11. 11.
    El-Feghi, I., Elmahjoub, F., Alswady, B., Baiou, A.: Offline Handwritten Arabic Words Recognition Using Zernike Moments and Hidden Markov Models. In: International Conference on Computer Applications and Industrial Electronics, ICCAIE, pp. 165–168 (2010)Google Scholar
  12. 12.
    Hamdi, R., Bouchareb, R., Bedda, M.: Handwritten Arabic Character Recognition Based on SVM Classifier. In: 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA, pp. 1–4 (2008)Google Scholar
  13. 13.
    Khalifa, M., BingRu, Y.: A Novel Word Based Arabic Handwritten Recognition System Using SVM Classifier. In: Shen, G., Huang, X. (eds.) ECWAC 2011, Part I. CCIS, vol. 143, pp. 163–171. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  14. 14.
    Almaádeed, S., Higgens, C., Elliman, D.: Recognition of Off-Line Handwritten Arabic Words Using Hidden Markov Model Approach. In: Proceedings of 16th International Conference on Pattern Recognition, vol. 3, pp. 481–484 (2002)Google Scholar
  15. 15.
    Ben Cheikh, I., Kacem, A.: Neural Network for the Recognition of Handwritten Tunisian City Names. In: 9th International Conference on Document Analysis and Recognition, pp. 1108–1112 (2007)Google Scholar
  16. 16.
    Benouareth, A., Ennaji, A., Sellami, M.: HMMs with Explicit State Duration Applied to Handwritten Arabic Word Recognition. In: 18th International Conference on Pattern Recognition, pp. 897–900 (2006)Google Scholar
  17. 17.
    Touj, S.M., Ben Amara, N.E., Amiri, H.: A Hybrid Approach for Off-Line Arabic Handwriting Recognition Based on a Planar Hidden Markov Modeling. In: 9th International Conference on Document Analysis and Recognition, ICDAR, pp. 964–968 (2007)Google Scholar
  18. 18.
    AlKhateeb, J.H., Khelifi, F., Jianmin, J., Ipson, S.S.: A New Approach for Off-Line Handwritten Arabic Word Recognition Using KNN Classifier. In: IEEE International Conference Signal and Image Processing Applications, pp. 191–194 (2009)Google Scholar
  19. 19.
    Nasien, D., Haronand, H., Yuhaniz, S.S.: Support Vector Machine (SVM) for English Handwritten Character Recognition. In: Second International Conference on Computer Engineering and Applications, pp. 249–252 (2010)Google Scholar
  20. 20.
    Nemmour, H., Chibani, Y.: Handwritten Arabic Word Recognition Based on Ridgelet Transform and Support Vector Machines. In: International Conference on High Performance Computing and Simulation, HPCS, pp. 357–361 (2011)Google Scholar
  21. 21.
    Kahraman, F., Capar, A., Ayvaci, A., Demirel, H., Gokmen, M.: Comparison of SVM and ANN Performance for Handwritten Character Classification. In: Proceedings of the 12th IEEE Signal Processing and Communications Applications Conference, pp. 615–618 (2004)Google Scholar
  22. 22.
    Vapnik, V.N.: An Overview of Statistical Learning Theory. IEEE Trans. Neural Networks 10, 988–999 (1999)CrossRefGoogle Scholar
  23. 23.
    Hsu, C.W., Lin, C.J.: A Comparison of Methods for Multiclass Support Vector Machines. IEEE Trans. Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  24. 24.
    Milgram, J., Cheriet, M., Sabourin, R.: One against One or One against All: Which One Is Better for Handwriting Recognition with SVMs? Presented at Tenth International Workshop on Frontiers in Handwriting Recognition (2006)Google Scholar
  25. 25.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA Data Mining Software: An Update. SIGKDD Explor. Newsl. 11, 10–18 (2009)CrossRefGoogle Scholar
  26. 26.
    Pechwitz, M., Snoussi Maddouri, S., Margner, V., Ellouze, N., Amiri, H.: IFN/ENIT-Database of Handwritten Arabic Words. In: 7th Colloque International Francophone sur lEcrit et le Document, CIFED, Hammamet, Tunis, pp. 21–23 (2002)Google Scholar
  27. 27.
    El-Melegy, M.T., Abdelbaset, A.A.: Global Features for Offline Recognition of Handwritten Arabic Literal Amounts. In: 5th International Conference on Information and Communications Technology, ITI, pp. 125–129 (2007)Google Scholar
  28. 28.
    Lorigo, L.M., Govindaraju, V.: Offline Arabic Handwriting Recognition: A Survey. IEEE Trans. Pattern Anal. Mach. Intell. 28, 712–724 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Abdulrahman Alalshekmubarak
    • 1
  • Amir Hussain
    • 1
  • Qiu-Feng Wang
    • 2
  1. 1.Dept. of Computing ScienceUniversity of StirlingScotland, UK
  2. 2.National Laboratory of Pattern Recognition(NLPR), Institute of AutomationChinese Academy of SciencesChina

Personalised recommendations