Design of a Multitask Neurovision Processor

  • George K. Knopf
  • Madan M. Gupta


The architecture of a biologically motivated visual-information processor that can perform a variety of tasks associated with the early stages of machine vision is described. The computational operations performed by the processor emulate the spatiotemporal information-processing capabilities of certain neural-activity fields found along the human visual pathway. The state-space model of the neurovision processor is a two-dimensional nural network of densely interconnected nonlinear processing elements PE’s. An individual PE represents the dynamic activity exhibited by a spatially localized population of excitatory and inhibitory nerve cells. Each PE may receive inputs from an external signal space as well as from the neighboring PE’s within the network. The information embedded within the signal space is extracted by the feedforward subnet. The feedback subnet of the neurovision processor generates useful steady-state and temporal-response characteristics that can be used for spatiotemporal filtering, short-term visual memory, spatiotemporal stabilization, competitive feedback interaction, and content-addressable memory. To illustrate the versatility of the multitask processor design for machine-vision applications, a computer simulation of a simplified vision system for filtering, storing, and classifying noisy gray-level images is presented.

Key words

neural-activity field neuro-vision processor spatio-temporal processing short-term visual memory spatio-temporal stabilization content addressable memory 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    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
  2. 2.
    L. Uhr, “Psychological motivation and underlying concepts, ” in Structured Computer Vision, S. Tanimoto and A. Klinger, (eds.), Academic Press: New York, 1980, pp. 1–30.Google Scholar
  3. 3.
    S.P. Levitan, C.C. Weems, A.R. Hanson, and E.H. Riseman, “The UMass image understanding architecture,” in Parallel Computer Vision, L. Uhr,ed., Academic Press: New York pp. 215–248.1987Google Scholar
  4. 4.
    S. Amari, “Mathematical foundations of neurocomputing,” Proc. IEEE, vol. 78, pp. 1443–1462, 1990.CrossRefGoogle Scholar
  5. 5.
    M.M. Gupta and G.K. Knopf, “A multi-task visual information processor with a biologically motivated design,” J Vis. Commun. Image Rep., vol. 3, No. 3, pp. 230–246, 1992.CrossRefGoogle Scholar
  6. 6.
    M.M. Gupta and G.K. Knopf, “A multi-task neuro-vision processor with extensive feedback and feedforward connections,” in Image Processing, K.-H. Taou, ed., Proc. Soc. Photo-Opt. Instrum. Eng., vol 1606, pp. 482–495, 1991.Google Scholar
  7. 7.
    K. Kishimoto and S. Amari, “Existence and stability of local excitations in homogenous neural fields,” J. Math. Biol., vol. 7, pp. 303–318, 1979.MathSciNetzbMATHCrossRefGoogle Scholar
  8. 8.
    G.K. Knopf, “Theoretical studies of a dynamic neurovision processor with a biologically motivated design,” Ph.D. dissertation, University of Saskatchewan, Canada, 1991.Google Scholar
  9. 9.
    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
  10. 10.
    S. Grossberg, “Nonlinear neural networks: principles, mechanisms and architectures,” Neural Net.,vol. 1, pp. 17–61, 1988.CrossRefGoogle Scholar
  11. 11.
    P.K. Simpson, Artificial Neural Systems, Pergamon Press: New York, 1991.Google Scholar
  12. 12.
    D.S. Levine, “Neural population modeling and psychology: a review,” Math. Biosci.,vol. 66, pp. 1–86, 1983.MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    R.C. Gonzalez and P. Wintz, Digital Image Processing, Addison-Wesley: Reading MA, 1977.zbMATHGoogle Scholar
  14. 14.
    M.D. Levine, Vision in Man and Machine, McGraw-Hill: New York, 1985.Google Scholar
  15. 15.
    L. Uhr, “Highly parallel, hierarchical, recognition cone perceptual structures,” in Parallel Computer Vision, L. Uhr, ed., Academic Press: New York: 1987, pp. 249–292.Google Scholar
  16. 16.
    H. Tunley, “Dynamic image segmentation and optic flow extraction,” in Proc. IEEE Int. Joint conf on Neural Networks, Seattle WA, 1991, vol. 1, pp. 599–604.CrossRefGoogle Scholar
  17. 17.
    H.R. Wilson, “Spatiotemporal characterization of a transient mechanism in the human visual system,” Vis. Res.,vol. 20, pp. 443–452, 1980.CrossRefGoogle Scholar
  18. 18.
    P.A. Anninos, B. Beek, T.J. Csermel, E.E. Harth, and G. Pertile, “Dynamics of neural structures,” J. Theor. Biol., vol. 26, pp. 121–148, 1970.CrossRefGoogle Scholar
  19. 19.
    A.J. Maren, C.T. Harston, and R.M. Pap, Handbook of Neural Computing Applications, Academic Press: San Diego, CA, 1990.zbMATHGoogle Scholar
  20. 20.
    J.J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities, Proc. Nat. Acad. Sci., USA, vol. 79, pp. 2554–2558, 1982.MathSciNetCrossRefGoogle Scholar
  21. 21.
    J.J. Hopfield and D.W. Tank, “Computing with neural circuits: a model,” Science, vol. 233, pp. 625–633, 1986.CrossRefGoogle Scholar
  22. 22.
    T. Kohonen, Self-Organization and Associative Memory,Springer-Verlag: Berlin, 1984.zbMATHGoogle Scholar
  23. 23.
    K. Fukushima, S. Miyake, and T. Ito, “Neo-cognitron: a neural network model for a mechanism of visual pattern recognition,” IEEE Trans. Sys., Man, Cybem., vol. 13, pp. 826–834, 1983.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1993

Authors and Affiliations

  • George K. Knopf
    • 1
  • Madan M. Gupta
    • 1
  1. 1.Intelligent Systems Research Laboratory and Centre of Excellence on Neuro-Vision Research (IRIS)College of Engineering, University of SaskatchewanSaskatoonCanada

Personalised recommendations