A Novel Word Based Arabic Handwritten Recognition System Using SVM Classifier

  • Mahmoud Khalifa
  • Yang BingRu
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 143)


Every language script has its structure, characteristic, and feature. Character based word recognition depends on the feature available to be extracted from character. Word based script recognition overcome the problem of character segmenting and can be applied for several languages (Arabic, Urdu, Farsi... est.). In this paper Arabic handwritten is classified as word based system. Firstly, words segmented and normalized in size to fit the DCT input. Then extract feature characteristic by computing the Euclidean distance between pairs of objects in n-by-m data matrix X. Based on the point’s operator of extrema, feature was extracted. Then apply one to one-Class Support Vector Machines (SVMs) as a discriminative framework in order to address feature classification. The approach was tested with several public databases and we get high efficiency rate recognition.


DCT Feature extraction Maxima FER SVM 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Goraine, H., Sher, M., Al-Emami, S.: Off-Line Arabic Character Recognition. Computer 25, 71–74 (1992)CrossRefGoogle Scholar
  2. 2.
    Al-Muhtaseb, H.A., Mahmoud, S.A., Qahwaji, R.S.: Recognition of offline printed Arabic text using Hidden Markov Models. Signal Processing 88, 2902–2912 (2008)CrossRefzbMATHGoogle Scholar
  3. 3.
    Jiang, J., Weng, Y., Li, P.: Dominant color extraction in DCT domain. Image and Vision Computing 24, 1269–1277 (2006)CrossRefGoogle Scholar
  4. 4.
    Wick, M.L.: Context-Sensitive Error Correction Using Topic Models to Improve OCR. In: International Conference on Document Analysis and Recognition (2007)Google Scholar
  5. 5.
    Benouareth, A., Ennaji, A., Sellami, M.: HMMs with explicit state duration applied to handwritten Arabic word recognition. In: Presented at 18th International Conference on Pattern Recognition, ICPR 2006 (2006)Google Scholar
  6. 6.
    Vinciarelli, A.: A survey on offline Cursive Word Recognition. Pattern Recognition 35, 1433–1446 (2002)CrossRefzbMATHGoogle Scholar
  7. 7.
    Rajput, G.G., Anita H. B.: Handwritten Script Recognition using DCT and Wavelet Features at Block Level. In: IJCA Special Issue on: Recent Trends in Image Processing and Pattern Recognition, RTIPPR (2010)Google Scholar
  8. 8.
    AIKhateeb, J.H.: Word-based Handwritten Arabic Scripts Recognition using DCT Features and Neural Network Classifier. In: 5th International Multi-Conference on Systems, Signals and Devices (2008)Google Scholar
  9. 9.
    AIKhateeb, J.H.: Multiclass Classification of Unconstrained Handwritten Arabic Words Using Machine Learning Approaches. The Open Signal Processing Journal 2, 21–28 (2009)CrossRefGoogle Scholar
  10. 10.
    Cao, J.: New Method of Feature Extraction Using Wavelet Transform and DCT in OCR. Journal of Optoelectronics Laser (2004)Google Scholar
  11. 11.
    Fujisawa, H., Liu, C.L.: Directional Pattern Matching For Character Recognition. In: Proc.7th ICDAR, Edinburgh, Scotland, pp. 794–798 (2003)Google Scholar
  12. 12.
    Rodríguez, J.A., Perronnin, F.: Local gradient histogram features for word spotting in Unconstrained handwritten documents (2008)Google Scholar
  13. 13.
    Zhang, Z., Jin, L., Ding, K., Gao, X.: Character-SIFT: a novel feature for offline handwritten Chinese character recognition. In: 10th International Conference on Document Analysis and Recognition (2009)Google Scholar
  14. 14.
    Günter, S.: Off-line cursive handwriting recognition using multiple classifier systems—on the influence of vocabulary, ensemble, and training set size. Optics and Lasers in Engineering 43, 437–454 (2005)CrossRefGoogle Scholar
  15. 15.
    Günter, S.: HMM-based handwritten word recognition: on the optimization of the number of states, training iterations and Gaussian components. Pattern Recognition 37, 2069–2079 (2004)CrossRefGoogle Scholar
  16. 16.
    Rath, T.M.: Features for Word Spotting in Historical Manuscripts. In: International Conference on Document Analysis and Recognition (ICDAR 2003). IEEE, Los Alamitos (2003) 0-7695-1960-1/03 $17.00Google Scholar
  17. 17.
    Hansen, E.R.: Global optimization using interval analysis: the one-dimensional case. Journal of Optimization Theory and Applications (1979)Google Scholar
  18. 18.
    Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Machine Learning 46, 389–422 (2002)CrossRefzbMATHGoogle Scholar
  19. 19.
    Wilpo, J., Rabiner, L.: A Modified K-Means Clustering algorithm for use in Isolated work. Recognition ASSP 33(3), 587–594 (1985)Google Scholar
  20. 20.
    Altuwaijri, M., Bayoumi, M.: Arabic Text Recognition using Neural Network. In: Proceedings of IEEE International Symposium on Circuits and Systems, London, Uk, pp. 415–418 (1994)Google Scholar
  21. 21.
    Hosseini, H., Bouzerdoum, A.: A system for Arabic character recognition. In: IEEE Proceeding of the International Conference on Information System, Brisbane, Australia, pp. 120–124 (1994)Google Scholar
  22. 22.
    Hassibi, K.: Machine- printed Arabic OCR using Neural Networks. In: The 4th International Conference and Exhibition on Mult-Lingual Computering, Cambridge, UK (1994)Google Scholar
  23. 23.
    Amin, A., Alsadon, H., Fisher, S.: Hand printed Arabic character recognition system using an artificial network. Pattern Recognition 29(4), 663–675 (1996)CrossRefGoogle Scholar
  24. 24.
    Almaadeed, S., Higgens, C., Elliman, D.: Recognition of off line hand witten Arabic words using hidden markov model approach. In: Proceedings of the 16th International Conference on Pattern Recognition, August 2002, vol. 3, pp. 481–484 (2002)Google Scholar
  25. 25.
    El-Hajj, R., Mokbel, C., Likforman-Sulem, L.: Arabic Handwriting Recognition Using BaselineDependant Features and Hidden Markov Modeling. In: Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition, ICDAR 2005 (2005)Google Scholar
  26. 26.
    Boser, B., Guyon, I., Vapnik, V.: A training algorithm for optimal margin classifiers. In: Haussler, D. (ed.) The Fifth Annual ACM Workshop on Computational Learning Theory, pp. 144–152 (1992)Google Scholar
  27. 27.
    Mahmud, S.A., Awaida, S.M.: Recognition Of Off-Line Handwritten Arabic (Indian) Numerals Using Multi-Scale Features And Support Vector Machines Vs. Hidden Markov Models. The Arabian Journal for Science and Engineering 34(2B)Google Scholar
  28. 28.
    Shanthi, N., Duraiswamy, K.: A novel SVM-based handwritten Tamil character recognition system. Pattern Anal. Applic. 13, 173–180 (2010)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Lei, H., Govindaraju, V.: Speeding Up Multi-class SVM by PCA and Feature Selection. In: Feature Selection in Data Mining (FSDM 2005), The 5th SIAM International Conference on Data Mining Workshop, California, USA (2005)Google Scholar
  30. 30.
    Pechwitz, M., Maddouri, S.S., Margner, V., Ellouzeand, N., Amiri, H.: IFN.’ENIT Database of Arabic Handwritten words. In: Colloque International Francophone sur l’Ecritet Ie Document (CIFED), pp. 127–136 (2002)Google Scholar
  31. 31.
  32. 32.
    Ma, J., Zhao, Y., Ahalt, S.: OSU svm classifier matlab toolbox (2002),
  33. 33.
    Chang, C., Lin, C.: Libsvm: a library for support vector machines (2001),

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mahmoud Khalifa
    • 1
  • Yang BingRu
    • 1
  1. 1.Information Engineering SchoolUniversity of Science and TechnologyBeijingChina

Personalised recommendations