A New Adaptive Zoning Technique for Handwritten Digit Recognition

  • Sebastiano Impedovo
  • Francesco Maurizio Mangini
  • Giuseppe Pirlo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


In this paper we present a new adaptive zoning technique based on Voronoi tessellation for the task of handwritten digit recognition. This technique extracts features according to an optimal zoning distribution, obtained by an evolutionary-strategy based search. Several experiments have been conducted on the MNIST and the USPS datasets to investigate the proposed approach. Comparisons with regular square zoning reveal that the presented zoning strategy achieves better results for any type of SVM classifier. Furthermore, the proposed zoning method shows that the combination of the adaptive zoning strategy with the Voronoi topology leads to find a distribution of zones able to improve accuracy significantly. As a matter of fact reached accuracies are close to the best algorithms.


Zoning Feature Extraction Support Vector Machines 


  1. 1.
    Beyer, H.-G.: The Theory of Evolution Strategy. Springer, New York (2001)CrossRefGoogle Scholar
  2. 2.
    Bromley, J., Sackinger, E.: Neural-network and k-nearest-neighbor-classifiers. TechnicalReport 11359-910819-16TM, ATT (1991) Google Scholar
  3. 3.
    Chang, C.-C., Lin, C.-J.: LIBSVM: A library for support vector machines,
  4. 4.
    de Berg, M., Cheong, O., van Kreveld, M., Overmars, M.: Computational Geometry: Algorithms and Applications. Springer, Berlin (2008)Google Scholar
  5. 5.
    Drucker, H., Schapire, R., Simard, P.: Boosting performance in neural networks. International Journalof Pattern Recognition and Artificial Intelligence 7, 705–719 (1993)CrossRefGoogle Scholar
  6. 6.
    Fogel, D.B.: An introduction to simulated evolutionary optimization. IEEE Transactions on Neural Networks 5(1), 3–14 (1994)CrossRefGoogle Scholar
  7. 7.
    Freitas, C.O.A., Oliveira, L.S., Bortolozzi, F.: Handwritten Character Recognition using nonsymmetrical perceptual zoning. IJPRAI 21(1), 1–21 (2007)Google Scholar
  8. 8.
    Gatos, B., Kesidis, A., Papandreou, A.: Adaptive Zoning Features for Character and Word Recognition. In: Proceedings of ICDAR 2011, pp. 1160–1164 (2011)Google Scholar
  9. 9.
    Hull, J.: A database for handwritten text recognition research. IEEE Transactions on Pattern Analysis and Machine Intelligence 16, 550–554 (1994)CrossRefGoogle Scholar
  10. 10.
    Impedovo, D., Pirlo, G., Modugno, R.: New Advancements in Zoning-Based Recognition of Handwritten Characters. In: Proceedings of ICFHR 2012, pp. 661–665 (2012)Google Scholar
  11. 11.
    Impedovo, S., Modugno, R., Pirlo, G.: Analysis of membership Functions for Voronoi-based Classification. In: Proceedings of ICFHR 2010, pp. 220–225 (2010)Google Scholar
  12. 12.
    Impedovo, S., Modugno, R., Pirlo, G.: Membership Functions for Zoning-based Recognition of Handwritten Digits. In: Proc. International Conference on Pattern Recognition, Istanbul, Turkey, pp. 1879–1879 (2010)Google Scholar
  13. 13.
    LeCun, Y., et al.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, vol. 86, pp. 2278–2324 (1998)Google Scholar
  14. 14.
    Liu, C.-L., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognition 36, 2271–2285 (2003)CrossRefzbMATHGoogle Scholar
  15. 15.
    Niu, X.X., Suen, C.Y.: A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recognition 45, 1318–1325 (2012)CrossRefGoogle Scholar
  16. 16.
    Oliveira, L.S., Sabourin, R., Bartolozzi, F., Suen, C.Y.: Automatic Recognition of Handwritten Numeral Strings: A Recognition and Verification Strategy. IEEE T-PAMI 24(11), 1438–1454 (2002)CrossRefGoogle Scholar
  17. 17.
    Radtke, P.V.W., Wong, T., Sabourin, R.: A Multi-objective Memetic Algorithm for Intelligent Feature Extraction. In: Coello Coello, C.A., Hernández Aguirre, A., Zitzler, E. (eds.) EMO 2005. LNCS, vol. 3410, pp. 767–781. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  18. 18.
    Rajashekararadhya, S.V., Ranjan, P.V.: Support Vector Machine based Handwritten Numeral Recognition of Kannada Script. In: Proc. IEEE International Conference on Advance Computing 2009, pp. 381–386 (2009)Google Scholar
  19. 19.
    Rasband, W.S.: ImageJ, U. S. National Institutes of Health, Bethesda, Maryland, USA,
  20. 20.
    Schölkopf, B., Smola, A.: Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, Cambridge (2002)Google Scholar
  21. 21.
    Sharma, D., Gupta, D.: Isolated Handwritten Digit Recognition using Adaptive Unsupervised Incremental Learning Technique. International Journal of Computer Applications 7(4), 27–33 (2010)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Simard, P., LeCun, Y., Denker, J.S.: Efficient pattern recognition using a new transformation distance. In: Advances in Neural Information Processing Systems 5, San Francisco, CA, USA, pp. 50–58 (1993)Google Scholar
  23. 23.
    Vamvakas, G., Gatos, B., Pratikakis, I., Stamatopoulos, N., Roniotis, A., Perantonis, S.J.: Hybrid off-line OCR for isolated handwritten Greek characters. In: Proc. 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications (SPPRA 2007), Innsbruck, Austria, pp. 197–202 (2007)Google Scholar
  24. 24.
    Xiang, P., Xiuzi, Y., Sanyuan, Z.: A hybrid method for robust car plate character recognition. Engineering Applications of Artificial Intelligence 18(8), 963–972 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sebastiano Impedovo
    • 1
  • Francesco Maurizio Mangini
    • 1
  • Giuseppe Pirlo
    • 1
  1. 1.Department of Computer ScienceUniversity of Bari “Aldo Moro”BariItaly

Personalised recommendations