Visual organization of illusory surfaces

  • Davi Geiger
  • Krishnan Kumaran
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1064)


A common factor in all illusory contour figures is the perception of a surface occluding part of a background. These surfaces are not constrained to be at constant depth and they can cross other surfaces. We address the problem of how the image organizations that yield illusory contours arise. Our approach is to iteratively find the most salient surface by (i) detecting occlusions; (ii) assigning salient-surface-states, a set of hypothesis of the local salient surface configuration; (iii, applying a Bayesian model to diffuse these salient-surface-states; and (iv) efficiently selecting the best image organization (set of hypothesis) based on the resulting diffused surface.

We note that the illusory contours arise from the surface boundaries and the amodal completions emerge at the overlapping surfaces. The model reproduces various qualitative and quantitative aspects of illusory contour perception.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    E. Adelson and P. Anandan. Ordinal characteristics of transparency. In Proc. AAAI Workshop on Qualitative Vision, pages 552–573, Los Angeles, CA, 1990.Google Scholar
  2. 2.
    D. J. Amit, H. Gutfreund, and H. Sompolinsky. Spin-glass models of neural networks. Physical Review A, 32:1007–1018, 1985.Google Scholar
  3. 3.
    M. Brady and W. E. L. Grimson. The perception of subjective surfaces. A.I. Memo No. 666, AI Lab., MIT, Nov. 1982.Google Scholar
  4. 4.
    T. Darrell and A. Pentland. Cooperative robust estimation using layers of support. IEEE Trans. PAMI, PAMI-17(5):474–487, 1995.Google Scholar
  5. 5.
    R. von der Heydt. E. Peterhans and G. Baumgartner. Neuronal responses to illusory contour stimuli reveal stages of visual cortical processing. In Visual Neuroscience, pages 343–351. Cambridge U.P, 1986.Google Scholar
  6. 6.
    D. Geiger and F. Girosi. Parallel and deterministic algorithms for mrfs: surface reconstruction. IEEE Trans. PAMI, PAMI-13(5):401–412, May 1991.Google Scholar
  7. 7.
    D. Geiger, B. Ladendorf, and A. Yuille. Binocular stereo with occlusion. In 2nd ECCV, Santa Marguerita, Italy, May 1992. Springer-Verlag.Google Scholar
  8. 8.
    D. Geiger and A. Yuille. A common framework for image segmentation. International Journal of Computer Vision, 6:3:227–243, August 1991.Google Scholar
  9. 9.
    G.Guy and G. Medioni. Inferring global perceptual contours from local features. In Proc. Image Understanding Workshop DARPA, September 1992.Google Scholar
  10. 10.
    S. Grossberg and E. Mingolla. Neural dynamics of perceptual grouping:textures, boundaries and emergent segmentations. Perception & Psychophysics, 38(2):141–170, 1985.Google Scholar
  11. 11.
    Stephen Grossberg. 3-d vision and figure-ground separation by visual cortex. Perception & Psychophysics, 55(1):48–120, 1994.Google Scholar
  12. 12.
    F. Heitger and R. von der Heydt. A computational model of neural contour processing: Figure-ground segregation and illusory contours. Proceedings of the IEEE, pages 32–40, 1993.Google Scholar
  13. 13.
    S. Hsu, P. Anandan, and S. Peleg. Accurate computation of optical flow by using layered motion representation. In ICPR, pages 743–746, Oct 1994.Google Scholar
  14. 14.
    D.A. Huffman. A duality concept for the analysis of polyhedral scenes. In Machine Intelligence, volume 6. Edinb. Univ. Press, Edinb., U.K., 1971.Google Scholar
  15. 15.
    Bela Julesz. Textons: the elements of texture perception, and their interactions. Nature, 290:91–97, March 1981.Google Scholar
  16. 16.
    A. Kamath and N. Karmarkar. A continuous approach to compute upper bounds in quadratic minimization problems with integer constraints. In C. A. Floudas and P. M. Pardalos, ed., Recent Adv. in Global Opt., volume 2, 229–241, 1991.Google Scholar
  17. 17.
    G. Kanizsa. Organization in Vision. Praeger, New York, 1979.Google Scholar
  18. 18.
    P.J. Kellman and T.F. Shipley. A theory of visual interpolation in object perception. Cognitive Psychology, 23:141–221, 1995.Google Scholar
  19. 19.
    K. Kumaran, D. Geiger, and L. Gurvits. Illusory surfaces and visual organization. Network:Computation in Neural Systems, 7(1), February 1996.Google Scholar
  20. 20.
    D. Mumford. Elastica and computer vision. In C. L. Bajaj, editor, Algebraic Geometry and Its Applications. Springer-Verlag, New York, 1993.Google Scholar
  21. 21.
    Nitzberg, Mumford, and Shiota. Filtering, Segmentation, and Depth. Springer-Verlag, New York, 1993.Google Scholar
  22. 22.
    M. Nitzberg and D. Mumford. The 2.1-d sketch. In Proceedings of the International Conference on Computer Vision, pages 138–144. IEEE, DC, 1990.Google Scholar
  23. 23.
    D. L. Ringach and R. Shapley. The dynamics of illusory contour integration. Investigative Ophthalmology and Visual Science, 35,#2:4196-, 1994.Google Scholar
  24. 24.
    D. L. Ringach and R. Shapley. Similar mechanisms for illusory contour and amodal completion. Investigative Ophthalmology and Visual Science, 35,#2:1089-, 1994.Google Scholar
  25. 25.
    A. Shashua and S. Ullman. Structural saliency: The detection of globally salient structures using a locally connected network. In Proceedings of the International Conference on Computer Vision, pages 321–327, 1988.Google Scholar
  26. 26.
    F. Shumann. Einige beobachtungen uber die zusammenfassung von gesichtseindrucken zu einheiten. Physiologische Studien, 1:1–32, 1904.Google Scholar
  27. 27.
    S. Ullman. Filling in the gaps: The shape of subjective contours and a model for their generation. Biological Cybernetics, 25:1–6, 1976.Google Scholar
  28. 28.
    R. von der Heydt, E. Peterhans, and G. Baumgartner. Illusory contours and cortical neuron responses. Science Washington, 224:1260–1262, 1984.Google Scholar
  29. 29.
    L. R. Williams and A.R. Hanson. Perceptual completion of occluded surfaces. Proc. of IEEE Computer Vision and Pattern Recognition, 1994.Google Scholar
  30. 30.
    L. R. Williams and D.W. Jacobs. Stochastic completion fields: A neural model of illusory contour shape and salience. Proc. of 5th Intl. Conf. on Comp. Vision, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Davi Geiger
    • 1
  • Krishnan Kumaran
    • 2
  1. 1.Courant InstituteNew York UniversityNew YorkUSA
  2. 2.Rutgers UniversityPiscatawayUSA

Personalised recommendations