Implementation of an artificial neural network for the segmentation of texture images

  1. Mosquera González, Antonio
  2. Cabello Ferrer, Diego
  3. Carreira Nouche, M. J.
  4. González Penedo, Manuel Francisco
Libro:
Panel '92: actas, XVIII Conferencia Latinoamericana de Informática

Editorial: Las Palmas de Gran Canarias : Universidad, 1992?

Ano de publicación: 1992

Páxinas: 838-845

Congreso: Conferencia Latinoamericana de Informática (18. 1992. Las Palmas de Gran Canaria)

Tipo: Achega congreso

Resumo

In this work we describe the implementation of an artificial neural network, an extension of Hopfield's model, for the segmentation of textured images. We use a Markov random field in order to model the textures in the image. The problem is approached in terms of the minimization of a cost function that is projected onto the network. It provides a locally optimal solution to the problem of the classification of M* M pixels into K classes (textures). The experimental results obtained on artificial and natural images show the validity of the architecture we propose