Structural Description to Recognising Arabie Characters Using Decision Tree Learning Techniques

  • Adnan Amin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)


Character recognition systems can contribute tremendously to the advancement of the automation process and can improve the interaction between man and machine in many applications, including office automation, cheque verification and a large variety of banking, business and data entry applications. The main theme of this paper is the automatic recognition of hand-printed Arabic characters using machine learning. Conventional methods have relied on hand-constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The advantages of machine learning are that it can generalize over the large degree of variation between writing styles and recognition rules can be constructed by example.The system was tested on a sample of handwritten characters from several individuals whose writing ranged from acceptable to poor in quality and the correct average recognition rate obtained using cross-validation was 87.23%.


Pattern Recognition Arabic characters Hand-printed characters Parallel thinning Feature extraction Structural classification Machine Learning C4.5 


  1. 1.
    V. Govindan and A. Shivaprasad, Character recognition-a review, Pattern Recognition, 23(7), pp. 671–683, 1990.CrossRefGoogle Scholar
  2. 2.
    S. Mori, C. Y. Suen and K. Yamamoto, Historical review of OCR research and development, Proceedings of the IEEE 80(7), pp. 1029–1058, 1992.CrossRefGoogle Scholar
  3. 3.
    E. Lecolinet E. and O. Baret, Cursive word recognition: Methods and strategies, Fundamentals in Handwriting Recognition, S. Impedovo, Ed. Springer-Verlag, 1994, pp. 235–263.Google Scholar
  4. 4.
    C. Y. Suen, R. Shingal and C. C. Kwan, Dispersion factor: A quantitative measurement of the quality of handprinted characters, Int. Conference of Cybernetics and Society, 1977, p. 681–685.Google Scholar
  5. 5.
    A. Amin, Offline Arabic characters Recognition: The State Of the Art, Pattern Recognition 31(5), 517–530, 1998.CrossRefMathSciNetGoogle Scholar
  6. 6.
    Quilan J. R., C4.5: programs for machine learning, San Mateo CA, Morgan Kauffman, 1993.Google Scholar
  7. 7.
    B.K. Jang and R.T. Chin, One-pass parallel thinning: analysis, properties, and quantitative evaluation, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-14, pp. 1129–1140, 1992.CrossRefGoogle Scholar
  8. 8.
    A. Amin, H. Al-Sadoun and S. Fischer, Hand-Printed Arabic Characters Recognition System Using an Artifial Network, Pattern Recognition 29(4), pp. 663–675, 1996.CrossRefGoogle Scholar
  9. 9.
    J. R. Quilan, Discovering rules for a large collection of examples, Edinburgh University Press, 1979.Google Scholar
  10. 10.
    L. Fu, Neural Networks in Computer Intelligence, McGraw-Hill, Singapore, pp. 331–348, 1994.Google Scholar
  11. 11.
    M. Stone, Cross-validatory choice and assessment of statistical predictions, Journal of the Royal Statistical Society 36(1), pp. 111–147, 1974.zbMATHGoogle Scholar
  12. 12.
    S. M. Weiss and G. E. Kulikowski, Computer systems that learn, Kauffinan, CA, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Adnan Amin
    • 1
  1. 1.School of Computer ScienceUniversity of New South WalesSydneyAustralia

Personalised recommendations