Evaluation of the use of two different models of neural networks in the classification of images based on textural features

Authors

  • Wonder Alexandre Luz Alves UNINOVE, São Paulo
  • Sidnei Alves de Araújo UNINOVE, São Paulo

DOI:

https://doi.org/10.5585/exacta.v4i1.655

Keywords:

Inteligência artificial. Processamento de imagens digitais. Reconhecimento de padrões. Redes neurais artificiais. Texturas.

Abstract

This work explores the classification of textures by artificial neural networks. Two different models of neural networks are used: one supervised (multiple layers perceptron) and the other non-supervised (Kohonen auto-organizable maps). In both cases, the attributes that describe the textures and those ones used to classify them, result from statistic approaches of first and second orders. In this study, a comparative analysis between the experimental results of each model of networks is carried out.

Downloads

Download data is not yet available.

Author Biographies

Wonder Alexandre Luz Alves, UNINOVE, São Paulo

Graduado em Ciência da Computação – Uninove.

Sidnei Alves de Araújo, UNINOVE, São Paulo

Mestre em Engenharia Elétrica – Mackenzie; Doutorando em Engenharia Elétrica – Poli-USP; Professor na graduação [Ciência da Computação] – Uninove.

Published

2008-03-12

How to Cite

Alves, W. A. L., & Araújo, S. A. de. (2008). Evaluation of the use of two different models of neural networks in the classification of images based on textural features. Exacta, 4(1), 77–86. https://doi.org/10.5585/exacta.v4i1.655