Publication Details

The use of the RCE Neural Network in a Pattern Recognition

ZBOŘIL, F.; ZBOŘIL, F. The use of the RCE Neural Network in a Pattern Recognition. 34th Spring International Conference Modelling and Simulation of Systems MOSIS 2000. Ostrava: 2000. p. 65-70. ISBN: 80-85988-44-5.
Czech title
Použití RCE neuronové sítě pro rozpoznávání obrazů
Type
conference paper
Language
English
Authors
Keywords

Neural Networks, RCE Classifier, Pattern Recognition

Abstract

A Restricted Coulomb Energy (RCE) neural network is a specific design of the
hypespherical classifier proposed by Reilly in 1982 and it is suitable for
classification of nonlinearly separable clusters of patterns in multidimensional
pattern spaces. The paper deals with the use of the RCE neural network for the
recognition of persons. Two sets of input patterns were used in described
experiments. The first set contained pictures of person faces and the second set
contained person fingerprints. The short principle and topology of the RCE neural
network, learning and retrieving algorithms and mentioned experiments are
described in the paper.

Annotation

The paper deals with the use of the RCE neural network for the recognition of persons. The short principle of the RCE neural network (topology, learning and retrieving) and mentioned experiments are described in the paper.

Published
2000
Pages
65–70
Proceedings
34th Spring International Conference Modelling and Simulation of Systems MOSIS 2000
Conference
34th Spring International Conference on Modeling and Simulation of Systems MOSIS 2000, Rožnov pod Radhoštěm, CZ
ISBN
80-85988-44-5
Place
Ostrava
BibTeX
@inproceedings{BUT5419,
  author="František {Zbořil} and František {Zbořil}",
  title="The use of the RCE Neural Network in a Pattern Recognition",
  booktitle="34th Spring International Conference Modelling and Simulation of Systems MOSIS 2000",
  year="2000",
  pages="65--70",
  address="Ostrava",
  isbn="80-85988-44-5"
}
Back to top