Learning a Classifier with Very Few Examples: Analogy Based and Knowledge Based Generation of New Examples for Character Recognition

  • S. Bayoudh
  • H. Mouchère
  • L. Miclet
  • E. Anquetil
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4701)


This paper is basically concerned with a practical problem: the on-the-fly quick learning of handwritten character recognition systems. More generally, it explores the problem of generating new learning examples, especially from very scarce (2 to 5 per class) original learning data. It presents two different methods. The first one is based on applying distortions on original characters using knowledge on handwriting properties like speed, curvature etc. The second one consists in generation based on the notion of analogical dissimilarity which quantifies the analogical relation “A is to B almost as C is to D”. We give an algorithm to compute the k-least dissimilar objects D, hence generating k new objects from three examples A, B and C. Finally, we experimentally prove the efficiency of both methods, especially when used in conjunction.


instance generation sequence generation by analogy knowledge-based generation handwritten character recognition 


  1. 1.
    Wolf, L., Martin, I.: Robust boosting for learning from few examples. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  2. 2.
    Bishop, C.: Training with noise is equivalent to Tikhonov regularization. Neural Computation 7(1), 108–116 (1995)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Cano, J., Pérez-Cortes, J.C., Arlandis, J., Llobet, R.: Training set expansion in handwritten character recognition. In: Proc. of the 9th Int. Workshop on Structural and Syntactic Pattern Recognition, pp. 548–556 (2002)Google Scholar
  4. 4.
    Simard, P., Steinkraus, D., Platt, J.C.: Best practice for convolutional neural network applied to visual analysis. In: Proc. of the 7th Int. Conf. on Document Analysis and Recognition (2003)Google Scholar
  5. 5.
    Varga, T., Bunke, H.: Generation of synthetic data for an HMM-based handwriting recognition system. In: Proc. of 7th Int. Conf. on Document Analysis and Recognition, pp. 618–622 (2003)Google Scholar
  6. 6.
    Bishop, C.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2007)Google Scholar
  7. 7.
    Anquetil, E., Lorette, G.: Perceptual model of handwriting drawing application to the handwriting segmentation problem. In: Proc. of the 4th Int. Conf. on Document Analysis and Recognition, pp. 112–117 (1997)Google Scholar
  8. 8.
    Hesse, M.: Aristotle’s logic of analogy. The Philosophical Quarterly 15(61), 328–340 (1965)CrossRefGoogle Scholar
  9. 9.
    Gentner, D., Holyoak, K.J., Kokinov, B.: The analogical mind: Perspectives from cognitive science. MIT Press, Cambridge (2001)Google Scholar
  10. 10.
    Lepage, Y.: Solving analogies on words: an algorithm. In: Proc. of COLING-ACL 1998, vol. 1, pp. 728–735 (1998)Google Scholar
  11. 11.
    Bayoudh, S., Miclet, L., Delhay, A.: Learning by analogy: a classification rule for binary and nominal data. In: Proc. of the Int. Joint Conf. on Artificial Intelligence, vol. 20, pp. 678–683 (2007)Google Scholar
  12. 12.
    Nilsson, N.: Principles of Artificial Intelligence. Tioga Publishing Company (1980)Google Scholar
  13. 13.
    Eppstein, D.: Finding the k shortest paths. SIAM J. Computing 28(2), 652–673 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Varga, T., Kilchhofer, D., Bunke, H.: Template-based synthetic handwriting generation for the training of recognition systems. In: Proc. of 12th Conf. of the International Graphonomics Society, pp. 206–211 (2005)Google Scholar
  15. 15.
    Plamondon, R., Guerfali, W.: The generation of handwriting with delta-lognormal synergies. Biological Cybernetics 78, 119–132 (1998)zbMATHCrossRefGoogle Scholar
  16. 16.
    Gillick, L., Cox, S.J.: Some statistical issues in the comparison of speech recognition algorithms. In: IEEE (ed.) Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Glasgow, Scotland, pp. 532–535. IEEE Computer Society Press, Los Alamitos (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • S. Bayoudh
    • 1
  • H. Mouchère
    • 2
  • L. Miclet
    • 1
  • E. Anquetil
    • 2
  2. 2.IRISA-INSA 

Personalised recommendations