Advertisement

A Biologically Motivated and Computationally Tractable Model of Low and Mid-Level Vision Tasks

  • Iasonas Kokkinos
  • Rachid Deriche
  • Petros Maragos
  • Olivier Faugeras
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3022)

Abstract

This paper presents a biologically motivated model for low and mid-level vision tasks and its interpretation in computer vision terms. Initially we briefly present the biologically plausible model of image segmentation developed by Stephen Grossberg and his collaborators during the last two decades, that has served as the backbone of many researchers’ work. Subsequently we describe a novel version of this model with a simpler architecture but superior performance to the original system using nonlinear recurrent neural dynamics. This model integrates multi-scale contour, surface and saliency information in an efficient way, and results in smooth surfaces and thin edge maps, without posterior edge thinning or some sophisticated thresholding process. When applied to both synthetic and true images it gives satisfactory results, favorably comparable to those of classical computer vision algorithms. Analogies between the functions performed by this system and commonly used techniques for low- and mid-level computer vision tasks are presented. Further, by interpreting the network as minimizing a cost functional, links with the variational approach to computer vision are established.

Keywords

Coarse Scale Simple Cell Illusory Contour Saliency Detection Feedback Term 
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.

References

  1. 1.
    Adelson, E., Bergen, J.: Spatiotemporal energy models for the perception of motion. JOSA 2(2), 284–299 (1985)CrossRefGoogle Scholar
  2. 2.
    Black, M., Sapiro, G., Marrimont, D., Heeger, D.: Robust anisotropic diffusion. IEEE Trans. on Image Processing 7(3), 421–432 (1998)CrossRefGoogle Scholar
  3. 3.
    Carandini, M., Heeger, D.: Summation and division by neurons in visual cortex. Science 264, 1333–1336 (1994)CrossRefGoogle Scholar
  4. 4.
    Canny, J.: A computational approach to edge detection. IEEE Trans. on PAMI 8(6), 679–698 (1986)Google Scholar
  5. 5.
    Cohen, M.A., Grossberg, S.: Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. on Systems, Man and Cybernetics 13(5), 815–826 (1983)zbMATHMathSciNetGoogle Scholar
  6. 6.
    Daugman, J.: Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filters. JOSA 2(7), 160–169 (1985)Google Scholar
  7. 7.
    Deriche, R.: Using Canny’s criteria to derive a recursively implemented optimal edge detector. IJCV 1(2), 167–187 (1987)CrossRefGoogle Scholar
  8. 8.
    Field, D., Hayes, A., Hess, R.: Contour integration by the human visual system: Evidence for a local ‘association field’. Vision Research 33(2), 173–193 (1993)CrossRefGoogle Scholar
  9. 9.
    Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the bayesian treatment of images. IEEE Trans. on PAMI 66(6), 721–741 (1984)Google Scholar
  10. 10.
    Grossberg, S.: Neural Networks and Natural Intelligence. MIT Press, Cambridge (1988)Google Scholar
  11. 11.
    Grossberg, S.: 3-d vision and figure-ground separation by visual cortex. Perception and Psychophysics 55, 48–121 (1994)CrossRefGoogle Scholar
  12. 12.
    Grossberg, S., Mingolla, E.: Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations. Perc. & Psych.s 38, 141–171 (1985)CrossRefGoogle Scholar
  13. 13.
    Grossberg, S., Mingolla, E.: Neural dynamics of surface perception: Boundary webs, illuminants, and shape from shading. CVGIP 37, 116–165 (1987)Google Scholar
  14. 14.
    Grossberg, S., Mingolla, E., Williamson, J.: Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation. Neural Networks 8(7-8), 1005–1028 (1995)CrossRefGoogle Scholar
  15. 15.
    Guy, G., Medioni, G.: Inferring global perceptual contours from local features. IJCV 20(1), 113–133 (1996)CrossRefGoogle Scholar
  16. 16.
    Heitger, F., von der Heydt, R.: A computational model of neural contour processing: Figure-ground segregation and illusory contours. In: Proc. ICCV, pp. 32–40 (1993)Google Scholar
  17. 17.
    Hopfield, J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. of the N.A.S. of USA 81, 3088–3092 (1984)CrossRefGoogle Scholar
  18. 18.
    Koch, C., Marroquin, J., Yuille, A.: Analog neuronal networks in early vision. MIT AI lab Technical report 751 (1985)Google Scholar
  19. 19.
    Lee, T.S.: A bayesian framework for understanding texture segmentation in the primary visual cortex. Vision Research 35, 2643–2657 (1995)CrossRefGoogle Scholar
  20. 20.
    Li, Z.: Visual segmentation by contextual influences via intracortical interactions in primary visual cortex. Network: Comput. Neur. Syst. 10, 187–212 (1999)zbMATHCrossRefGoogle Scholar
  21. 21.
    Mumford, D.: Elastica and computer vision. In: Bajaj, J. (ed.) Algebraic Geometry and its applications, pp. 507–518. Springer, Heidelberg (1993)Google Scholar
  22. 22.
    Neumann, H., Sepp, W.: Recurrent V1-V2 interaction in early visual boundary processing. Biological Cybernetics 91, 425–444 (1999)CrossRefGoogle Scholar
  23. 23.
    Parent, P., Zucker, S.W.: Trace inference, curvature consistency, and curve detection. IEEE Trans. on PAMI 11(8), 823–839 (1989)Google Scholar
  24. 24.
    Perona, P., Malik, J.: Detecting and localizing edges composed of steps, peaks and roofs. In: Proc. ICCV, pp. 52–57 (December 1990)Google Scholar
  25. 25.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. on PAMI 12(7), 629–639 (1990)Google Scholar
  26. 26.
    Sha’ashua, A., Ullman, S.: Structural saliency: the detection of globally salient structures using a locally connected network. In: Proc. ICCV, pp. 321–327 (1988)Google Scholar
  27. 27.
    Ren, X., Malik, J.: A probabilistic multi-scale model for contour completion based on image statistics. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 312–327. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  28. 28.
    Williams, L.R., Jacobs, D.W.: Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation 9(4), 837–858 (1997)CrossRefGoogle Scholar
  29. 29.
    Yuille, A.: Energy functions for early vision and analog networks. MIT A.I. lab technical report, 987 (1987)Google Scholar
  30. 30.
    Yuille, A., Geiger, D.: A common framework for image segmentation. IJCV 6, 227–243 (1991)CrossRefGoogle Scholar
  31. 31.
    Kokkinos, R., Deriche, O.: Faugeras and P. Maragos Towards bridging the gap between biological and computational segmentation. INRIA Research Report (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Iasonas Kokkinos
    • 1
  • Rachid Deriche
    • 2
  • Petros Maragos
    • 1
  • Olivier Faugeras
    • 2
  1. 1.School of Electrical and Computer EngineeringNational Technical University of AthensGreece
  2. 2.INRIASophia-Antipolis CedexFrance

Personalised recommendations