Gaussian Synapse Networks for Handwritten Character Recognition

  • J. L. Crespo
  • R. J. Duro
Conference paper


In the context of improved higher order neural architectures for pattern recognition we have made use of a new type of higher order network containing gaussian synapses and developed the Gaussian Synapses Backpropagation Algorithm (GSBP) for the implementation of different types of pattern detectors. This paper concentrates on the presentation of the algorithm and its comparison to other structures in a typical benchmark problem i.e. the recognition of handwritten characters. The inclusion of gaussian functions in the synapses of the network allows the training algorithm to select the appropriate spatial information and filter out all that is irrelevant according to the training it has received. With this strategy it is possible to obtain very good recognition results with hardly any preprocessing and independently of backgrounds and slant using small networks that are quite easy to train.


Optical Character Recognition Handwriting Recognition Handwritten Character Curve Network Handwritten Character Recognition 
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]
    Plamondon, R. and Srihari, S. N.: On-Line and OffLine Handwriting Recognition: A Comprehensive Survey IEEE Trans on PAMI, V22, N1, (2000), 63–84.CrossRefGoogle Scholar
  2. [2]
    Seong-Whan Lee and Hee-Heon Song: A New Recurrent Neural Network Architecture for Visual Pattern Recognition, IEEE Trans on Neural Networks V8., N2, (1997), 331–339.CrossRefGoogle Scholar
  3. [3]
    Gori, M., Scarselli, F.: Are Multilayer Perceptrons Adequate for Pattern Recognition and Verification?, IEEE Trans on PAMI, Vol 20. No. 11 (1998) 1121–1132.CrossRefGoogle Scholar
  4. [4]
    Duro, R.J., Crespo, J.L., and Santos, J.: Training Higher Order Gaussian Synapses. Lecture Notes in Computer Science, Vol 1606 Springer-Verlag, Berlin (1999) 537–545.Google Scholar
  5. [5]
    Suen C.Y., Nadal, C., Legault, R, May, T. A. and Lam, L.: Computer Recognition of Handwritten Numerals, Proc IEEE, V80, (1992),1162–1180.Google Scholar
  6. [6]
    Moms, I.P. and Dlay, S. S.: The DSFPN, a New Neural Network for Optical Character Recognition, IEEE Trans on Neural Networks, V10, N6, (1999), 1465–1473.CrossRefGoogle Scholar
  7. [7]
    Kim, G., Govindaraju, V. and Srihari, S. N.: An Architecture for Handwritten Text Recognition Systems, Int′l J. Document Analysis and Recognition 2 (1999),37–44.CrossRefGoogle Scholar
  8. [8]
    Shustorovich, A. and Thrasher, C. W.:Neural Network Positioning and Classification of Handwritten Characters, Neural Networks, V9, N4, (1996), 685–693.Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • J. L. Crespo
  • R. J. Duro
    • 1
  1. 1.Grupo de Sistemas AutónomosUniversidade da CoruñaSpain

Personalised recommendations