Advertisement

Neural Processing Letters

, Volume 1, Issue 1, pp 25–29 | Cite as

Texture segmentation using pyramidal Gabor functions and self-organising feature maps

  • A. Guérin-Dugué
  • P. M. Palagi
Article

Abstract

This paper presents texture segmentation realised with image treatment methods and an artificial neural network model. Gabor oriented filters are used to extract frequential texture features and Self-Organising Feature Maps are used to group and interpolate these features. In order to decrease the number of filters, we use a pyramidal multiresolution method of image representation. We intend to build an architecture inspired by the early stages of the visual cortex, while making local frequential analysis of the images, which must be able to segment different textured images.

Keywords

Neural Network Artificial Neural Network Network Model Nonlinear Dynamics Visual Cortex 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    J.G. Daugman. Uncertainty relation for resolution in space, spatial frequency, and orientation by twodimensional visual cortical filters,J.Opt.Soc.Ame.A, vol. 2, no. 7, pp. 1160–1169, 1985.ADSGoogle Scholar
  2. [2]
    T. Kohonen.Self-organisation and associative memory, Springer Verlag, Berlin, 1984.Google Scholar
  3. [3]
    A.C. Bovik, M. Clark, W.S. Geissler. Multichannel texture analysis using localised spatial filters,IEEE Trans. Patt. Anal. Machine Intelligence, vol. 48, no. 1, pp. 55–73, 1990.Google Scholar
  4. [4]
    R. Young. The Gaussian derivative theory of spatial vision: analysis of cortical cell receptive field line-weighting profiles,Tech. Rep. GMR-4920 (General Motor Researc), Warren, Mich., 1985.Google Scholar
  5. [5]
    J. Malik, P. Perona. Preattentive texture discrimination with early vision mechanisms,J.Opt.Soc.Ame.A, vol.7, no.5, May 1990.Google Scholar
  6. [6]
    F. Heitger et al. Simulation of neural contour mechanisms: from simple to end-stopped cells,Vision Research, vol. 32, no. 5, pp. 963–981, 1992.Google Scholar
  7. [7]
    E. Oja. Self-organising maps and computer vision, in:Neural networks for perception, Volume 1 — Human and machine perception, Harry Wechsler ed., Academic Press Inc., San Diego, 1992.Google Scholar
  8. [8]
    S. Lu et al. Texture segmentation by clustering of Gabor feature vectors,IJCNN'91, vol. I, p. 683, 1991.Google Scholar
  9. [9]
    L. Tomasini.Apprentissage d'une représentation statistique et topologique d'un environnement. Ph.D. Dissertation, Ecole Nationale de l'Aeronautique et de l'Espace, February 1993.Google Scholar
  10. [10]
    A. Chehikian. Algorithmes optimaux pour la génération de pyramides d'images passe-bas et laplaciennes,Traitement du signal, vol. 9, no. 4, pp. 297–307, 1992.Google Scholar
  11. [11]
    P.G. Schyns. A modular neural network model of concept acquisition,Cognitive Sciences, vol. 15, pp. 461–508, 1991.Google Scholar

Copyright information

© Kluwer Academic Publishers 1994

Authors and Affiliations

  • A. Guérin-Dugué
    • 1
  • P. M. Palagi
    • 1
  1. 1.Laboratoire de Traitement d'Images et Reconnaissance de FormesInstitut National Polytechnique de GrenobleGrenoble CedexFrance

Personalised recommendations