Wilson—Cowan Neural-Network Model in Image Processing

  • Kari Mantere
  • Jussi Parkkinen
  • Timo Jaaskelainen
  • Madan M. Gupta


The neural-network model based on the theory proposed by Wilson and Cowan has been simulated by using digitized real images. Mathematically, the model is based on coupled nonlinear differential equations that describe the functional dynamics of cortical nervous tissue, and the model can operate in different dynamical modes, depending on coupling strengths. The model is shown to store images in reduced form and to recognize edges of an object. Examples of how the network processes input images are shown.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    H.R. Wilson and J.D. Cowan, “Excitatory and inhibitory interactions in localized populations of model neurons,” Biophys. J.,vol. 12, pp. 1–24, 1972.CrossRefGoogle Scholar
  2. 2.
    H.R. Wilson and J.D. Cowan, “A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue,” Kybernetik,vol. 13, pp. 55–80, 1973.zbMATHCrossRefGoogle Scholar
  3. 3.
    H. Sakaguchi, “Oscillatory and excitable behaviours in a population of model neurons,” Prog. Theor. Phys.,vol. 79, pp. 1061–1068, 1988.CrossRefGoogle Scholar
  4. 4.
    M.M. Gupta and G.K. Knopf, “A dynamic neural network for visual memory,” in Visual Communications and Image Processing ‘80: Fifth in a Series, M. Kunt, ed., Proc. Soc., Photo-Opt. Instrum. Eng., vol. 1360, pp. 1044–1055, 1990.Google Scholar
  5. 5.
    J.L. Homer (ed.), Optical Signal Processing, Academic Press: San Diego, CA, 1987.Google Scholar

Copyright information

© Springer Science+Business Media New York 1993

Authors and Affiliations

  • Kari Mantere
    • 1
  • Jussi Parkkinen
    • 2
  • Timo Jaaskelainen
    • 3
  • Madan M. Gupta
    • 4
  1. 1.Department of Applied PhysicsUniversity of KuopioKuopioFinland
  2. 2.Department of Computer Science and Applied MathematicsUniversity of KuopioKuopioFinland
  3. 3.Department of PhysicsUniversity of JoensuuJoensuuFinland
  4. 4.Intelligent Systems Research Laboratory, College of EngineeringUniversity of SaskatchewanSaskatoonCanada

Personalised recommendations