Dynamic Handwriting Recognition Based on an Evolutionary Neural Classifier

  • Stéphane Gentric
  • Lionel Prevost
  • Maurice Milgram
Conference paper


At the present time, most of the classification problems have to deal with heterogeneous data presenting a strong variability, even within a class. It seems therefore relevant to substitute to the notion of class, the notion of sub-class, the latter regrouping a relatively homogeneous sub-set of examples. In order to generate these sub-classes (and models that are associated them) automatically, we developed an evolutionary neural classifier. At the beginning, it is made of as many networks as the number of classes of the problem. During the training, the number of networks evolves in order to modelize to the best the different sub-classes and to decrease the overall confusion rate between classes. An application of this classifier is the recognition of unconstrained dynamic handwriting: the multiplication of character models (called allographs) makes essential the automatie sub-class generation. Results, tested on some 25000 letters of the Unipen database are very encouraging.


Word Recognition Radial Basis Function Network Handwriting Recognition Homogeneous Subset Signature Authentication 
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]
    Bengio Y., LeCun Y., Nohl C. & Burges C., LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition, Neural Computation, 7(6), 1289–1303, 1995.CrossRefGoogle Scholar
  2. [2]
    Bontempi B. & Marcelli A., A genetic learning system for on-line character recognition, ICPR’94, 83–87, 1994.Google Scholar
  3. [3]
    Garcia-Salicetti S., Dorizzi B., Gallinari P. & Wimmer Z., Adaptive Discrimination in an HMM-based neural predictive system for on-line word recognition, ICPR’96, (D), 515–519,1996.Google Scholar
  4. [4]
    Gentric P., Handwritten character recognition using neural networks,ICOHD’93, pp 13–15,1993.Google Scholar
  5. [5]
    Gentric S. & Milgram M, Reconnaissance de mots cursifs et génération non supervisée de sous-classes, CIFED’98, pp 384–393, 1998.Google Scholar
  6. [6]
    Guyon I., Albrecht P., LeCun Y., Denker J. & Hubbard W., Design of a Neural Network Character Recognizer for a Touch Terminal, Pattern Recognition, 24(2), 105–119, 1991.CrossRefGoogle Scholar
  7. [7]
    Guyon I., Schomaker L., Plamondon R., Liberman M. & Janet S., UNIPEN project of on-line data exchange and recognizer benchmarks, ICPR’94, pp. 29–33, 1994.Google Scholar
  8. [8]
    Manke S., Finke M. & Waibel A., Combining Bitmaps with Oynamic Writing Information for On-Line Handwriting Recognition, ICPR’94, 596–598, 1994.Google Scholar
  9. [9]
    Manke S., Finke M. & Waibel A., Npen++: a writerindependent large vocabulary on-line handwriting recognition system, ICDAR’95, pp 403–408, 1995.Google Scholar
  10. [10]
    Morasso P., Barberis L., Pagliano S. & Vergano D., Recognition experiments of cursive dynamic handwriting with self-organising networks, Pattern Recognition, 26(3), 451–460,1996.CrossRefGoogle Scholar
  11. [11]
    Prevost L. & Milgram M., Modelizing character allographs in omni-scriptor frame: a new nonsupervised algorithm, Pattern Recognition Letters, 21(4), pp 295–302, 2000.CrossRefGoogle Scholar
  12. [12]
    Schwenk H. & Milgram M., Constraint tangent distance for on-line character recognition, ICPR’96, (D), 520–524, 1996.Google Scholar
  13. [13]
    Schenkel M., Guyon I. & Henderson D., On-line Cursive Script Recognition using Time-Delay Neural Networks and Hidden Markov Models, Machine Vision and Applications, (8), pp 215–223, 1995.Google Scholar
  14. [14]
    Simard P., Le Cun Y. & Denker J., Efficient pattern recognition using a new transformation distance, NIPS (5), pp 50–58, 1993.Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • Stéphane Gentric
  • Lionel Prevost
  • Maurice Milgram
    • 1
  1. 1.LISIF / PARCUniversité Pierre & Marie CurieParis cedex 05France

Personalised recommendations