Handwritten Digit Recognition Using Soft Computing Tools

  • V. Susheela Devi
  • M. Narasimha Murty
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 42)


This chapter deals with the handwritten digit recognition problem. We use a variety of classifiers for solving this problem. These classifiers include: nearest neighbour classifiers and fuzzy classifiers. A major contribution of this chapter is concerned with prototype selection for pattern classification. Genetic algorithms, simulated annealing, and tabu search are used for this purpose. The performance of various classifiers is compared based on experimental results obtained using a large data set of training and test patterns.


Simulated Annealing Classification Accuracy Tabu Search Test Pattern Training Pattern 
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.
    Suen, C.Y., Nadal, C, Legault, R., Mai, T.A., Lam, L. (1992): Computer Recognition of Unconstrained Handwritten Numerals. Proceedings of the IEEE 80, 1162–1180.CrossRefGoogle Scholar
  2. 2.
    O’Gorman, L., Kasturi, R. (1997): Document Image Analysis. IEEE Computer Society Press, Los Alamitos, Washington, Brussels, Tokyo.Google Scholar
  3. 3.
    Jain, A.K., Dubes, R.C. (1995): Pattern Recognition, Course # CPS 802 Notes, 1st Edition, Michigan State University, East Lansing, CAPCO, Oklahoma.Google Scholar
  4. 4.
    Hart, P.E. (1968): The Condensed Nearest Neighbour Rule. IEEE Trans, on Information TheoryIT-14, 515–516.CrossRefGoogle Scholar
  5. 5.
    Holmstrom, L., Koistinen, P., Laaksonen, J., Oja, E. (1997): Neural and Statistical Classifiers — Taxonomy and Two Case Studies. IEEE Trans, on Neural NetworksNN-8, 5–17.CrossRefGoogle Scholar
  6. 6.
    Duda, R.O., Hart, P.E. (1973): Pattern Classification and Scene Analysis, 1stEdition, John Wiley & Sons, New York, London, Sydney, Toronto.MATHGoogle Scholar
  7. 7.
    Smith, S.J., Bourgoin, M.O., Sims, K., Voorhees, H.L. (1994): Handwritten Character Classification Using Nearest Neighbour in Large Databases. IEEE Trans, on Pattern Analysis and Machine IntelligencePAMI-16, 915–919.CrossRefGoogle Scholar
  8. 8.
    Chang, E.I., Lippmann, R.P. (1990): Using Genetic Algorithms to Improve Pattern Classification Performance. In: Lippmann, R.P., Moody, J.E.,Touretzky, D.S. (Eds.): Advances in Neural Information Processing Systems 3. Morgan Kaufmann, 797–803.Google Scholar
  9. 9.
    Anderberg, M.R. (1973): Cluster Analysis for Applications, Academic Press, London.MATHGoogle Scholar
  10. 10.
    Klir, G.J., Yuan, B. (1997): Fuzzy Sets and Fuzzy Logic Theory and Applications Prentice-Hall of India, New Delhi.Google Scholar
  11. 11.
    Kim, T.,Bezdek, J.C, Hathaway, R.J. (1988):Optimal Tests for the Fixed Points of the Fuzzy C-Means Algorithm. Pattern Recognition21, 651–663.MathSciNetMATHCrossRefGoogle Scholar
  12. 12.
    Goldberg, D. (1989): Genetic Algorithms in Search, Optimization and Machine Learning, 1stEdition. Addison-Wesley, Reading.MATHGoogle Scholar
  13. 13.
    Kirkpatrick, S., Gelatt Jr., CD., Vecchi, M.P. (1983): Optimization by Simulated Annealing. Science 220.Google Scholar
  14. 14.
    Al-Sultan, K.S. (1995): A Tabu Search Approach to the Clustering Problem. Pattern Recognition28, 1443–1451.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • V. Susheela Devi
    • 1
  • M. Narasimha Murty
    • 1
  1. 1.Department of Computer Science and AutomationIndian Institute of ScienceBangaloreIndia

Personalised recommendations