Advertisement

Applications of Cellular Neural Networks for Shape from Shading Problem

  • Mariofanna Milanova
  • Paulo E. M. Almeida
  • Jun OkamotoJr.
  • Marcelo Godoy Simões
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1715)

Abstract

The Cellular Neural Networks (CNN) model consist of many parallel analog processors computing in real time. CNN is nowadays a paradigm of cellular analog programmable multidimensional processor array with distributed local logic and memory. One desirable feature is that these processors are arranged in a two dimensional grid and have only local connections. This structure can be easily translated into a VLSI implementation, where the connections between the processors are determined by a cloning template. This template describes the strength of nearest-neighbour interconnections in the network. The focus of this paper is to present one new methodology to solve Shape from Shading problem using CNN. Some practical results are presented and briefly discussed, demonstrating the successful operation of the proposed algorithm.

Keywords

Markov Random Field Cellular Neural Network Relaxation Algorithm Hopfield Network Hopfield 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chua, L.O. and Yang, L. “Cellular Neural Networks: Theory and Applications”, IEEE Trans. on Circuits and Systems, (CAS), Vol.35 (1988), 1257–1290zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Chua, L.O. and Roska, T. “The CNN Paradigm. IEEE Transactions on Circuits and Systems (Part I)”, CAS-40, 3 (1993), 147–156CrossRefGoogle Scholar
  3. 3.
    Roska, T. and Vandewalle, J. Cellular Neural Networks. (John Wiley&Sons), (1993)Google Scholar
  4. 4.
    Poggio, T., Torre, V. and Koch, C. “Computational Vision and Reqularisation Theory”, Nature, Vol. 317 (1985), 314–319CrossRefGoogle Scholar
  5. 5.
    Koch, C., Marroquin, J. and Yuille, A. “Analog Neural Networks in Early Vision”, Proc. Natl. Acad. Sci. USA, Vol. 83 (1986), 4263–4267MathSciNetGoogle Scholar
  6. 6.
    Wechsler, H. Computer Vision, Academic Press, Inc, (1990)Google Scholar
  7. 7.
    Pajares, G., Cruz, J. and Aranda, J. “Relaxation by Hopfield Network in Stereo Image Matching”, Patter Recognition, Vol. 31, No 5 (1998), 561–574CrossRefGoogle Scholar
  8. 8.
    Radvanti A. “Structural Analysis of Stereograms for CNN Depth Detection”, IEEE Trans. Circuits Syst. I, Vol. 46 (1999), 239–252CrossRefGoogle Scholar
  9. 9.
    Lithon, F. and Dragomirescu, D.“A Cellular Analog Network for MRF­Based Motion Detection”, IEEE Trans. Circuits Syst. I, Vol 46 (1999), 281–293CrossRefGoogle Scholar
  10. 10.
    Liu, D. and Michel, A. “Sparsely Interconnected Neural Networks for Associative Memories with Applications to Cellular Neural Networks”. IEEE Transactions on Circuits and Systems Part II Analog and Digital Signal Processing, Vol. 41, No. 4 (1994), 295–307zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Horn, B.K.P. “Obtaining Shape from Shading Information”. In The Psychology of Computer Vision, Winston, P.H., (Ed.). New York, McGraw-Hill, (1975), 115–155Google Scholar
  12. 12.
    Yu, S.S. and Tsai, W.H. “Relaxation by the Hopfield Neural Network”, Pattern Recognition, No. 25(2), (1992), 197–209CrossRefGoogle Scholar
  13. 13.
    Horn, B.K.P. “Local Shading Analysis”, IEEE Trans. Pattern Anal. Machine Intelligence, Vol. PAMI-16, No. 2 (Mar 1984), 170–184Google Scholar
  14. 14.
    Pentland, A.P., “Linear Shape from Shading”, Int. J. Comput. Vision, Vol. 4 (1990), 153–162CrossRefGoogle Scholar
  15. 15.
    Tsai, P.S. and Shah, M. “Shape from Shading using Linear Approximation”, Research Report, University of Central Florida, (1995)Google Scholar
  16. 16.
    Zheng, Q. and Chellapa, R. “Estimation of Illuminant Direction, Albedo, and Shape from Shading”, IEEE Trans. Pattern Anal. Machine Intelligence, Vol. 13, No. 7 (Jul1991), 680–702CrossRefGoogle Scholar
  17. 17.
    Grimson, W.E.L. From Images to Surfaces: A Computational Study of the Human Early Visual System, MIT Press, Cambridge, MA, (1981)Google Scholar
  18. 18.
    Lehky and Sejnowski. “Network Model of Shape from Shading: Neural Function Arises from both Receptive and Projective Fields”, Nature, Vol. 333 (Jun 1988), 452–454CrossRefGoogle Scholar
  19. 19.
    Wei, G. and Hirzinger, G. ”Learning Shape from Shading by a Multilayer Network”, IEEE Trans. On Neural Networks, Vol. 7, No. 4 (Jul 1996), 985–995CrossRefGoogle Scholar
  20. 20.
    Hopfield, J. and Tank, D. “Neural Computation of Decisions in Optimization Problems”, Biological Cybernetics, Vol.52 (1985), 141–152zbMATHMathSciNetGoogle Scholar
  21. 21.
    Bose, N.K. and Liang, P. Neural Network Fundamentals with Graphs, Algorithms and Applications, McGraw-Hill Series in Electrical and Computer Engineering, (1996)Google Scholar
  22. 22.
    Geman, S. and Geman, D. “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images”, IEEE Trans. Patter Anal. Machine Intelligence, Vol. PAMI-6, No. 6 (Nov 1984), 721–741CrossRefGoogle Scholar
  23. 23.
    Besag, J. “On the Statistical Analysis of Dirty Pictures“, J. R. Statist. Soc. B, Vol. 48, No. 3 (1986), 259–302zbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Mariofanna Milanova
    • 1
  • Paulo E. M. Almeida
    • 2
  • Jun OkamotoJr.
    • 1
  • Marcelo Godoy Simões
    • 1
  1. 1.Department of Mechanical EngineeringEscola Politécnica - USP2231 - São PauloSP - BRAZIL
  2. 2.Department of Research and PostgraduateCEFET - MG7675 - Belo HorizonteMG - BRAZIL

Personalised recommendations