Multigrid MRF based picture segmentation with cellular neural networks

  • László Czúni
  • Tamáss Szirányi
  • Josiane Zerubia
Segmentation and Grouping
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)


Due to the large computation power needed in image processing methods based on Markovian Random Field (MRF) [6], new variations of basic MRF models are implemented. The Cellular Neural Network [5,14,15] (CNN) architecture, implemented in real VLSI circuits, is of superior speed in image processing. This very fast CNN can implement the ideas of existing MRF models. which would result in real-time processing of images. On the other hand this VLSI solution gives new tasks since the CNN has a special local architecture [4], but it is already shown that a type of MRF image segmentation with Modified Metropolis Dynamics (MMD [9]) can be well implemented in the CNN architecture [18]. In this paper, we address the improvement of the existing CNN method [17]. We have tested different multigrid models and compared segmentation results. The main reason for this research is to find proper implementation of the CNN-MRF technique on CNNs taking into consideration the abilities of today's and future's VLSI CNN systems.


Image Segmentation Markovian Random Field Anisotropic Diffusion Cellular Neural Network Markovian Random Field Model 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R. Azencott: Parallel Simulated Annealing: Parallelization techniques, Wiley, 1992.Google Scholar
  2. 2.
    J. Besag: Spatial interaction and the statistical analysis of lattice systems, Jl. Roy. Statis. Soc. B. 36., 1974.Google Scholar
  3. 3.
    C. A. Bouman, M. Saphiro: A Multiscale Random Field Model for Bayesian Image Segmentation, IEEE Trans. Image Proc, Vol. 3, pp. 162–177, 1994.CrossRefGoogle Scholar
  4. 4.
    L.O. Chua, L. Yang: Cellular Neural Networks, IEEE Trans. on Circuit and Systems, Vol. 35, pp. 1257–1295, 1988.CrossRefGoogle Scholar
  5. 5.
    S. Espejo, R. Carmona, R. Dominguez-Castro, A. Rodriguez-Vazquez: A CNN Universal Chip in CMOS Technology, Int. J. of Circuit Theory and Appl.,Vol. 24, pp. 93–110, 1996.CrossRefGoogle Scholar
  6. 6.
    S. Geman and D. Geman: Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.6, pp.721–741, 1984.Google Scholar
  7. 7.
    C. Graffigne, F. Heitz, P. Pérez, F. Preteux, M. Sigelle, J. Zerubia: Hierarchical Markov random field models applied to image analysis, SPIEConf, San Diego, July 10–11 1995.Google Scholar
  8. 8.
    F. Heitz, P. Perez, P. Bouthemy: Multiscale minimisation of global energy functions in some visual recovery problems, CVGIP: Image Understanding, Vol.59. pp. 125–134, Jan. 1994.CrossRefGoogle Scholar
  9. 9.
    Z. Kató, J. Zerubia, M. Berthod: Satellite image classification using a modified Metropolis dynamics, Proc. ICASSP, San Francisco, March 1992.Google Scholar
  10. 10.
    Z. Kató, J. Zerubia, M. Berthod: A Hierarchical Markov Random Field Model and Multitemperature Annealing for Parallel Classification. Graphical:Models and Image Processing, Vol. 58, No. 1, pp. 18–37, January, 1996.CrossRefGoogle Scholar
  11. 11.
    S. Kirkpatrick, C. Gellatt, M. Vecchi: Optimisation by simulated annealing, Science 220, pp. 671–690, 1983.Google Scholar
  12. 12.
    N. Metropolis, A.W. Rosenbluth and M.N. Rosenbluth, A.H. Teller and E. Teller: Equation of State Calculations by Fast Computing Machines. J. of Chemical Physics, Vol.21, No.6, pp. 1087–1092, 1953.CrossRefGoogle Scholar
  13. 13.
    P. Perona, J. Malik: Scale space and edge detection using anisotropic diffusion, IEEE Tr. Pattern Analysis amd Machine Int,Vol.12,No.7, pp. 629–639,1990.CrossRefGoogle Scholar
  14. 14.
    T. Roska, L. O. Chua: The CNN Universal Machine: An Analogic Array Computer. IEEE Trans. on Circuits and Systems-II, Vol. 40, pp. 163–173, March 1993.CrossRefGoogle Scholar
  15. 15.
    T. Roska, T. Szirânyi: Classes of analogic CNN algorithms and their practical use in complex image processing tasks, Proc. IEEE Nonlinear Signal and Image Proc., pp.767–770, 1995.Google Scholar
  16. 16.
    T. Szirânyi, L. Czúni: Picture Segmentation with introducing an Anisotropic Preliminary Step to an MRF Model with Cellular Neural Networks. Proc. of the ICPR. IEEE, Vienna, 1996.Google Scholar
  17. 17.
    T. Szirányi, J. Zerubia: Markov Random Field Image Segmentation using Cellular Neural Network. IEEE Tr. Circuits and Systems L, Vol. 44, pp. 86–89, January, 1997.CrossRefGoogle Scholar
  18. 18.
    T. Szirányi, J. Zerubia, D. Geldreich, Z. Kato: Cellular Neural Network in Markov Random Field Image Segmentation, CVNA'96, IEEE,,Seville, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • László Czúni
    • 1
  • Tamáss Szirányi
    • 2
  • Josiane Zerubia
    • 3
  1. 1.Dep. of Image Processing and NeurocomputingUniversity of VeszprémEgyetem u. 10
  2. 2.Analogical and Neural Computing Laboratory, Computer and Automation InstituteHungarian Academy of SciencesKende u.Hungary
  3. 3.INRIA, Sophia-AntipolisSophia-Antipolis CedexFrance

Personalised recommendations