The random neural network model on the color pattern recognition problem

The purpose of this paper is to describe the use of the multiple classes random neural network model to recognize patterns having different colors. We propose a learning algorithm for the recognition of color patterns based upon the non-linear equations of the multiple classes random neural network...

Full description

Bibliographic Details
Main Author: José Aguilar
Format: Article
Language:English
Published: Universidad del Zulia
Series:Revista Técnica de la Facultad de Ingeniería
Subjects:
Online Access:http://www.scielo.org.ve/scielo.php?script=sci_arttext&pid=S0254-07702005000100005&lng=en&tlng=en
Description
Summary:The purpose of this paper is to describe the use of the multiple classes random neural network model to recognize patterns having different colors. We propose a learning algorithm for the recognition of color patterns based upon the non-linear equations of the multiple classes random neural network model using gradient descent of a quadratic error function. In addition, we propose a progressive retrieval process with adaptive threshold value. The experimental evaluation shows that our approach provides good results.
ISSN:0254-0770