Advertisement

CR-Modified SOM to the Problem of Handwritten Digits Recognition

  • Ehsan MohebiEmail author
  • Adil Bagirov
Conference paper

Abstract

Recently, researchers show that the handwritten digit recognition is a challenging problem. In this paper first, we introduce a Modified Self Organizing Maps for vector quantization problem then we present a Convolutional Recursive Modified SOM to the problem of handwritten digit recognition. The Modified SOM is novel in the sense of initialization process and the topology preservation. The experimental result on the well known digit database of MNIST, denotes the superiority of the proposed algorithm over the existing SOM-based methods.

Keywords

Input Image Convolutional Neural Network Trained Network Linear Manifold Handwritten Digit 
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.

References

  1. 1.
    Batista, L.B., Gomes, H.M., Herbster, R.F.: Application of growing hierarchical self-organizing map in handwritten digit recognition. In: Proceedings of 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI), pp. 1539–1545 (2003)Google Scholar
  2. 2.
    Cecotti, H., Belaíd, A.: A new rejection strategy for convolutional neural network by adaptive topology. In: Kurzyn̈ski, M., Puchala, E., Woz̈niak, M., Zolnierek, A. (eds.) Computer Recognition Systems, Advances in Soft Computing, vol. 30, pp. 129–136. Springer, Berlin (2005)Google Scholar
  3. 3.
    Horio, K., Yamakawa, T.: Handwritten character recognition based on relative position of local features extracted by self-organizing maps. Int. J. Innovative Comput. Inf. Control 3(4), 789–798 (2007)Google Scholar
  4. 4.
    Kohonen, T.: Self-Organizing Maps. Springer Series in Information Sciences, Berlin (2001)CrossRefzbMATHGoogle Scholar
  5. 5.
    Kohonen, T., Kaski, S., Lappalainen, H.: Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM. In: Neural Computation, pp. 1321–1344 (1997)Google Scholar
  6. 6.
    Ontrup, J., Ritter, H.: A hierarchically growing hyperbolic self-organizing map for rapid structuring of large data sets. In: Proceedings of 5th Workshop On Self-Organizing Maps, pp. 471–478 (2005)Google Scholar
  7. 7.
    Ontrup, J., Ritter, H.: Large-scale data exploration with the hierarchically growing hyperbolic SOM. Neural Netw.: Official J. Int. Neural Netw. Soc. 19(6–7), 751–761 (2006)CrossRefzbMATHGoogle Scholar
  8. 8.
    Shah-Hosseini, H.: Binary tree time adaptive self-organizing map. Neurocomputing 74(11), 1823–1839 (2011)CrossRefGoogle Scholar
  9. 9.
    Uchida, S., Sakoe, H.: A survey of elastic matching techniques for handwritten character recognition. IEICE—Trans. Inf. Syst. E88-D(8), 1781–1790 (2005)Google Scholar
  10. 10.
    Yang, L., Ouyang, Z., Shi, Y.: A modified clustering method based on self-organizing maps and Its applications. Procedia Comput. Sci. 9, 1371–1379 (2012)CrossRefGoogle Scholar
  11. 11.
    Zheng, H., Cunningham, P., Tsymbal, A.: Adaptive offset subspace self-organizing map: an application to handwritten digit recognition. In: Proceedings of Seventh International Workshop on Multimedia Data Mining, pp. 29–38 (2006)Google Scholar
  12. 12.
    Zheng, H., Cunningham, P., Tsymbal, A.: Learning multiple linear manifolds with self-organizing networks. Int. J. Parallel, Emergent Distrib. Syst. 22(6), 417–426 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Zheng, H., Shen, W., Dai, Q., Hu, S., Lu, Z.M.: Learning nonlinear manifolds based on mixtures of localized linear manifolds under a self-organizing framework. Neurocomputing 72(13–15), 3318–3330 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.School of Science, Information Technology and Engineering Federation University AustraliaBallaratAustralia

Personalised recommendations