Share Email Print
cover

Proceedings Paper

Mixed neural-traditional classifier for character recognition
Author(s): Andrzej Stajniak; Jaroslaw Szostakowski; Slawomir Skoneczny
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

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

Paper Details

Date Published: 7 February 1997
PDF: 9 pages
Proc. SPIE 2949, Imaging Sciences and Display Technologies, (7 February 1997); doi: 10.1117/12.266360
Show Author Affiliations
Andrzej Stajniak, Warsaw Univ. of Technology (Poland)
Jaroslaw Szostakowski, Warsaw Univ. of Technology (Poland)
Slawomir Skoneczny, Warsaw Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 2949:
Imaging Sciences and Display Technologies
Jan Bares; Christopher T. Bartlett; Paul A. Delabastita; Jose Luis Encarnacao; Nelson V. Tabiryan; Panos E. Trahanias; Arthur Robert Weeks, Editor(s)

© SPIE. Terms of Use
Back to Top