Advertisement

An architecture for texture segmentation: from energy features to region detection

  • P. M. Palagi
  • A. Guérin-Dugué
Neural Networks for Perception
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)

Abstract

This paper presents a texture segmentation model realised with image treatment processing and artificial neural network techniques. Gabor oriented filters are used to extract texture features and Self-Organising Feature Maps to group these features. In order to decrease the number of filters needed to better extract features, we use a multiresolution procedure and a learning rule property to features interpolation. Two main axes of texture recognition are exploited with this model; one by the interpolating capabilities of the feature space, leading to a segmentation based on the number of chosen filters; and the other by the unsupervised segmentation of textured regions, leading to the number of textured objects on the image. Also presented, is a proposition to improve the model by an active learning for features fusion, and where the detection of contours in low resolution levels are used to control the focus on the textured regions of the immediately posterior resolution level.

Keywords

Energy Feature Gabor Filter Resolution Level Texture Region Texture Segmentation 
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.
    Ahalt, S. C. et al. Competitive Learning Algorithms for Vector Quantization, Neural Networks, Vol. 3, 277–290 (1990).Google Scholar
  2. 2.
    Brodatz, P. Textures: A photographic Album for artists and designers. Dover Publications Inc., New York (1966).Google Scholar
  3. 3.
    Chehikian, A. Algorithmes optimaux pour la génération de pyramides d'images passe-bas et laplaciennes. Traitement du signal, Vol. 9, No. 4, 297–307 (1992).Google Scholar
  4. 4.
    Chu, C. C. & Aggrawal, J. K. Image interpretation using multiple sensing modalities. IEEE Trans. Patt. Anal. Mach. Inteligence, Vol. 14, No. 8, August (1992).Google Scholar
  5. 5.
    Daugman, J. G. Uncertainty relation for resolution in space, spatial frequency, and orientation by two-dimensional visual cortical filters. J. Opt. Soc. Ame. A, Vol.2, No.7, 1160–1169 (1985).Google Scholar
  6. 6.
    Demartine, P. Analyse de données par réseaux de neurones auto-organisés. Ph.D. Dissertation, Institut Nationale Polytechnique de Grenoble, December (1994).Google Scholar
  7. 7.
    Ghosh, J. & Bovik, A. C. Neural Networks for Textured Image Processing, in Artificial Neural Networks and Statistical Pattern Recognition: Old and News Connections. Elsevier Science Publishers, 55–73 (1991).Google Scholar
  8. 8.
    Grossberg, S. Competitive learning: From interactive activation to adaptive resonance. Cognitive Science, Vol. 23, 23–63 (1987).Google Scholar
  9. 9.
    Guérin-Dugué, A. & Palagi, P.M. Texture segmentation using pyramidal Gabor functions. Neural Processing Letters, Vol. 1, No. 1, 25–29 (1994).Google Scholar
  10. 10.
    Guérin-Dugué, A. & Palagi, P. M. Implantations de Filtres de Gabor par Pyramide d'Images Passe-Bas. Submitted to Traitement du Signal (1995)Google Scholar
  11. 11.
    Heitger, F. & al. Simulation of Neural Contour Mechanisms: from Simple to End-stopped Cells. Vision Research 32(5) 963–981 (1992).PubMedGoogle Scholar
  12. 12.
    Hubel, D. H. & Wiesel, T. N. Functional architecture of macaque monkey visual cortex. Proc. R. Soc. Lond. B. Vol. 198, 1–59 (1977).PubMedGoogle Scholar
  13. 13.
    Julesz, B. Texton Gradients: The Texton Theory Revisited. Biol. Cybern. Vol. 54, 245–251 (1986).PubMedGoogle Scholar
  14. 14.
    Kohonen, T. Self organisation and Associative Memories. Springer Verlag, Berlin (1984).Google Scholar
  15. 15.
    Kohonen, T. Self-Organisation maps: Optimization approaches. In T. Kohonen, K. Mäkísara, O. Simula, and J. Kangas, editors, Artificial Neural Networks: Proc. ICANN-91, II 981–990. North-Holland (1991).Google Scholar
  16. 16.
    Lovell, R. et all. A model of visual texture discrimination using multiple weak operators and spatial averaging. Pattern Recognition, Vol. 25, No. 10, 1157–1170 (1992).Google Scholar
  17. 17.
    Lu, S. & al. Texture Segmentation by Clustering of Gabor Feature Vectors. IJCNN I-683 (1991).Google Scholar
  18. 18.
    Malik, J. & Perona, P. Preattentive texture discrimination with early vision mechanisms. J.Opt.Soc.Ame.A, Vol.7, No.5, May (1990).Google Scholar
  19. 19.
    Marcelja, S. Mathematical description of the responses of simple cortical cells. J.Opt.Soc.Ame.A, Vol.70, No.11, 1297–1300 (1980).Google Scholar
  20. 20.
    Navarro, A. & Tabernero, A. Gaussian Wavelet Transform: Two Alternative Fast Implementations for Images. Multidimensional Systems and Signal Processing, Vol. 2,î 421–436 (1990).Google Scholar
  21. 21.
    Oja, E. Self-Organising Maps and Computer Vision. Neural Networks for Perception. Ed. Harry Wechsler. Volume 1 — Human and Machine Perception. Academic Press Inc. San Diego (1992).Google Scholar
  22. 22.
    Polen, D. & Ronner, S. Phase Relationships Between Adjacent Simple Cells in the Visual Cortex. Science, Vol.212, 1409–1411 (1981).PubMedGoogle Scholar
  23. 23.
    Schyns, P. G. & Oliva, A. From Blobs to Boundary Edges: Evidence for Time-and Spatial-Scale-Dependent Scene Recognition. Psychological Science, Vol. 5, No. 4, July (1994).Google Scholar
  24. 24.
    Tomasini, L. 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
  25. 25.
    Turner, M. R. Texture Discrimination by Gabor Functions. Biol. Cybem, Vol. 55, 71–82 (1986).Google Scholar
  26. 26.
    Young, R. The Gaussian derivative theory of spatial vision: analysis of cortical cell receptive field line-weighting profiles. Tec. Rep. GMR-4920 General Motors Research, Warren, Mich, USA (1985).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

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

Personalised recommendations