Skip to main content
Springer Nature Link
Log in

Texture image segmentation using a modified Hopfield network

  • Conference paper
  • First Online:
New Trends in Neural Computation (IWANN 1993)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 686))

Included in the following conference series:

  • 288 Accesses

Abstract

In this work we describe the implementation of an artificial neural network, an extension of Hopfield's model, for the supervised 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 objective function which integrates statistical and spatial information and which 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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. P. Brodatz. “Textures: A photographic album for artistis & designers”. Dover Publications, New York, 1966.

    Google Scholar 

  2. R. Chellappa. “Two-dimensional discrete Gaussian Markov random field models for image processing”, in Progress in Pattern Recognition 2 (L.N Kanal and A. Rosenfeld, Eds.), pp. 79–112, Elsevier, New York, 1985.

    Google Scholar 

  3. R. Chellappa and S. Chatterjee. Classification of textures using Gaussian Markov Random fields. IEEE Trans. Acoustic, Speech and Signal Processing, vol. ASSP-33, n. 4, pp. 959–963. 1985.

    Google Scholar 

  4. S.F. Cohen and D.V, Cooper. “Simple Parallel Hierarchical and Relaxation Algorithms for Segmenting Noncausal Markovian Random Fields”. IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 195–219, 1987.

    Google Scholar 

  5. G.R. Cross and A.K. Jain. “Markov random field texture models”. IEEE Trans. Pattern. Anal. Machine Intell., vol. PAMI-5, pp. 25–39, 1983.

    Google Scholar 

  6. M. Hassner and J. Sklansky. “The use of Markov random fields as model of texture”. Comput. Graphics Image Processing, vol. 12, pp. 357–370, 1980.

    Google Scholar 

  7. Chung-Lin Huang. “Parallel image segmentation using modofied Hopfield model”. Pattern Recognition Letters vol. 13, pp. 345–353, 1992.

    Google Scholar 

  8. J.J. Hopfield and D. W. Tank. “Computing with Neural Circuits: A model”. Science, vol. 233, pp. 625–633, 1986.

    Google Scholar 

  9. R.L. Kashyap and R. Chellappa. “Estimation and Choice of Neighbors in Spatial-Interaction Model of Images”. IEEE Trans. Information Theory, vol. IT-29, pp. 60–72, 1983.

    Google Scholar 

  10. R.L. Kashyap and A. Khotanzad. A sthocastic model based technique for texture segmentation. Seventh International Conference on Pattern Recognition, Montreal, 1984, pp. 1202–1205.

    Google Scholar 

  11. B.S. Manjunath, Tal Simchony and R. Chellappa. “Stochastic and deterministic networks for texture segmentation”. IEEE Trans. Acoust., Speech, Signal Process. vol. 38, pp. 1039–1049, 1990.

    Google Scholar 

  12. A. Mosquera, D. Cabello, M.J. Carreira and M.G. Penedo. “Unsupervised textured image segmentation using Markov random field and clustering algorithms”. In Computer Analysis of Images and Patterns (R. Klette, Ed.). Research in Informatics, vol. 5, pp. 139–147, Akademie Verlag, Berlin, 1991.

    Google Scholar 

  13. A. Mosquera, D. Cabello, J.M. Mallo, M.J. Carreira and M.G. Penedo. “Functional Neighborhood in Markov Random Fields: Generalized Texture Models”. The 8th Sacandinavian Conference on Image Analysis. Tromsø, Norway, may, 1993.

    Google Scholar 

  14. A.L. Vickers and J.W. Modestino. A maximum likelihood approach to texture classification. IEEE Trans. Pattern Anal. Machine Intell. vol. PAMI-4, n.1, pp. 61–68, 1982.

    Google Scholar 

  15. J.W. Woods. Two-dimensional discrete Markivian Fields. IEEE Trans. Information Theory, vol. IT-18, n.2, pp. 232–240, 1972.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Departamento de Electrónica y Computación. Facultad de Física, Universidad de Santiago de Compostela, 15706, Santiago de Compostela, Spain

    A. Mosquera, D. Cabello, M. J. Carreira & M. G. Penedo

Authors
  1. A. Mosquera
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. Cabello
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. J. Carreira
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. M. G. Penedo
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

José Mira Joan Cabestany Alberto Prieto

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Mosquera, A., Cabello, D., Carreira, M.J., Penedo, M.G. (1993). Texture image segmentation using a modified Hopfield network. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_217

Download citation

  • DOI: https://doi.org/10.1007/3-540-56798-4_217

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-56798-1

  • Online ISBN: 978-3-540-47741-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics