Advanced Neural Networks Methods for Recognition of Handwritten Characters

  • Sławomir Skoneczny
  • Jarosław Szostakowski
Conference paper


In this paper, we present the efficient voting classifier for the recognition of handwritten characters. This system consists of three voting nonlinear classifiers: two of them base on the multilayer perceptron, and one uses the moments method. The combination of these kinds of systems showed superiority of neural techniques applied with classical against exclusive traditional approach and resulted in high percentage of correctly recognized characters. Also, we present a comparison of the recognition results.


Feature Vector Character Recognition Multilayer Perceptron Moment Method Handwritten Character 
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]
    Y. Le Cun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, “Handwritten Digit Recognition with a Back-Propagation Network,” in Advances in Neural Information Processing Systems 2 (D. S. Touretzky, ed.), pp. 396–404, San Mateo, CA: Kaufmann, 1990.Google Scholar
  2. [2]
    S. Skoneczny, R. Foltyniewicz, and J. Szostakowski, “Neural Network Based Classifiers as Useful Tools in Zip Code Recognition Task,” in Proc. NOLTA’93, vol. 3, (Hawaii, USA), pp. 941–944, December 1993.Google Scholar
  3. [3]
    S. Kahan, T. Pavlidis, and H. S. Baird, “On the Recognition of Printed Characters of Any Font and Size,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-9, pp. 274–288, March 1987.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Sławomir Skoneczny
    • 1
  • Jarosław Szostakowski
    • 1
  1. 1.Institute of Control & Industrial Electronics (ISEP)Warsaw University of TechnologyWarszawaPoland

Personalised recommendations