Performance Study of a Regularization-Based Deformable Handwritten Recognition Approach

  • Yoshiki Mizukami
  • Shinya Nakanishi
  • Katsumi Tadamura
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


This study clarifies the accuracy performance of a deformable handwritten recognition approach (DHRA) for digit characters. The deformable approach consists of regularization-based displacement computation, coarse-to-fine strategy, distance measurement and k-nearest neighborhood method. We focus on several conditions for investigating the accuracy and the sensitivity, that is, the definition of averaging area in regularization process, regularization parameters and the number of k for k-nearest neighborhood method. According to the simulation results, it was shown that the proposed method has the error rate of 0.42% for MNIST handwritten digit database, resulting in the top-group of the performances reported until now.


deformable handwritten recognition MNIST digit database regularization 


  1. 1.
    Plamondon, R., Srihari, S.N.: On-Line and off-Line handwriting recognition: a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 63–84 (2000)CrossRefGoogle Scholar
  2. 2.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  3. 3.
    Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: 7th International Conference on Document Analysis and Recognition, pp. 958–963 (2003)Google Scholar
  4. 4.
    Ranzato, M., Boureau, Y.-L., LeCun, Y.: Sparse feature learning for deep belief networks. In: Advances in Neural Information Processing Systems, vol. 20, pp. 1–8 (2007)Google Scholar
  5. 5.
    Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4), 193–202 (1980)CrossRefzbMATHGoogle Scholar
  6. 6.
    Ciresan, D., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional neural network committees for handwritten character classification. In: 11th International Conference on Document Analysis and Recognition, pp. 1250–1254 (2011)Google Scholar
  7. 7.
    Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: International Conference on Computer Vision and Pattern Recognition, pp. 3642–3649 (2012)Google Scholar
  8. 8.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer (1995)Google Scholar
  9. 9.
    DeCoste, D., Scholkopf, B.: Training invariant support vector machines. Machine Learning 46, 161–190 (2002)CrossRefzbMATHGoogle Scholar
  10. 10.
    Liu, C., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognition 36(10), 2271–2285 (2003)CrossRefzbMATHGoogle Scholar
  11. 11.
    Niu, X.X., Suen, Y.: A novel hybrid CNN-SVM classifier for recognizing handwritten digits. Pattern Recognition 45(4), 1318–1325 (2012)CrossRefGoogle Scholar
  12. 12.
    Widrow, B.: The ‘Rubber-Mask’ Technique - I. Pattern Measurement and Analysis. Pattern Recognition 5(3), 175–198 (1973)CrossRefGoogle Scholar
  13. 13.
    Gregory, R.L.: Eye and brain, the Psychology of Seeing. World University Library. McGraw-Hill, New York (1966)Google Scholar
  14. 14.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 509–522 (2002)CrossRefGoogle Scholar
  15. 15.
    Keysers, D., Deselaers, T., Gollan, C., Ney, H.: Deformation models for image recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1422–1435 (2007)CrossRefGoogle Scholar
  16. 16.
    Uchida, S., Sakoe, H.: A monotonic and continuous two-dimensional warping based on dynamic programming. In: 14th International Conference on Pattern Recognition, vol. 1, pp. 521–524 (1998)Google Scholar
  17. 17.
    Mizukami, Y., Koga, K.: A handwritten Character recognition system using hierarchical displacement extraction algorithm. In: 13th International Conference on Pattern Recognition, vol. 3, pp. 160–164 (1996)Google Scholar
  18. 18.
    Mizukami, Y., Tadamura, K.: GPU implementation of deformable pattern recognition using prototype-parallel displacement computation. In: International Workshop on Image Registration in Deformable Environments - DEFORM 2006, vol. 1, pp. 71–80 (2006)Google Scholar
  19. 19.
    Mizukami, Y., Tadamura, K., Warrell, J., Li, P., Prince, S.: CUDA implementation of deformable pattern recognition and its application to MNIST handwritten digit database. In: 20th International Conference on Pattern Recognition, vol. 1, pp. 2001–2004 (2010)Google Scholar
  20. 20.
    Poggio, T., Torre, V., Koch, C.: Computational vision and regularization theory. Nature 317, 314–319 (1985)CrossRefGoogle Scholar
  21. 21.
    March, R.: Computation of stereo disparity using regularization. Pattern Recognition Letters 8(3), 181–188 (1988)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Yoshiki Mizukami
    • 1
  • Shinya Nakanishi
    • 1
  • Katsumi Tadamura
    • 1
  1. 1.Yamaguchi UniversityUbeJapan

Personalised recommendations