Complexity, Confusion, and Perceptual Grouping. Part II: Mapping Complexity

  • Benoit Dubuc
  • Steven W. Zucker


Intermediate-level vision is central to form perception, and we outline an approach to intermediate-level segmentation based on complexity analysis. In this second of a pair of papers, we continue the focus on edge-element grouping, and the motivating example of an edge element inferred from an unknown image. Is this local edge part of a long curve, or part of a texture? If the former, which is the next element along the curve? If the latter, is the texture like a well-combed hair pattern, in which nearby elements are oriented similarly, or more chaotic, as in a spaghetti pattern? In the previous paper we showed how these questions raise issues of complexity and dimensionality, and how context in both position and orientation are important. We now propose a measure based on tangential and normal complexities, and illustrate its computation. Tangential complexity is related to extension; normal complexity to density. Taken together they define four canonical classes of tangent distributions: those arising from curves, from texture flows, from turbulent textures, and from isolated “dust”. Examples are included.

perceptual organization segmentation complexity curve detection texture 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    T. Alter and R. Basri, “Extracting salient contours from images: An analysis of the salience network,” in Proc. of the IEEE CVPR, IEEE Comp. Society, pp. 13–20, 1996.Google Scholar
  2. 2.
    A. Antonini and M.P. Stryker, “Development of individual geniculocortical arbors in cat striate cortex and effects of binocular impulse blockade,” J. Neuroscience, Vol. 13, No. 8, 3549–3573, 1993.Google Scholar
  3. 3.
    F. Attneave, “Some informational aspects of visual perception,” Psychological Review, Vol. 61, pp. 183–193, 1954.Google Scholar
  4. 4.
    G. Borgefors, “Distance transformations in arbitrary dimensions,” Computer Vision, Graphics and Image Processing, Vol. 27, pp. 321–345, 1984.Google Scholar
  5. 5.
    G. Borgefors, “Distance transformations in digital images,” Computer Vision, Graphics and Image Processing, Vol 34, pp. 344–371, 1986.Google Scholar
  6. 6.
    P. Breton, “Recovering shape from shading and contour,” Ph.D. thesis, McGill University, Dept. of Electrical Engineering, Montréal, 1994.Google Scholar
  7. 7.
    T.M. Cover and J.A. Thomas, Elements of Information Theory, Wiley: New York, 1991.Google Scholar
  8. 8.
    B. Dubuc, “On estimating fractal dimension,” Master's Thesis, McGill University, Dept. of Electrical Engineering, Montréal, 1998.Google Scholar
  9. 9.
    B. Dubuc, “On the complexity of curves and the representation of visual information,” Ph.D. thesis, McGill University, Dept. of Electrical Engineering, Montréal, 1995.Google Scholar
  10. 10.
    S. Dubuc, and B. Dubuc, “Error bounds on the estimation of fractal dimension,” SINUM, Vol. 33, No. 2, pp. 602–626, 1996.Google Scholar
  11. 11.
    B. Dubuc, -F. Quiniou, C. Roques-Carmes, C. Tricot, and S.W. Zucker, “Evaluating the fractal dimension of profiles,” Phys. Rev. A, Vol. 39, No. 3, pp. 1500–1512, 1989.Google Scholar
  12. 12.
    B. Dubuc and S.W. Zucker, “Indexing visual representations through the complexity map,” in Proc. of the 5th ICCV, Cambridge, MA, 1995, IEEE Comp. Society, pp. 142–149.Google Scholar
  13. 13.
    B. Dubuc and S.W. Zucker, “Complexity, confusion, and perceptual grouping. Part I: The curve-like representation,” this issue, 2000.Google Scholar
  14. 14.
    Y. DuPain, T. Kamae, and M. Mendès-France, “Can one measure the temperature of a curve?,” Arch. of Rat. Mech. and Anal., pp. 155–163, 1986.Google Scholar
  15. 15.
    K.J. Falconer, Fractal Geometry: Mathematical Foundations and Applications. John Wiley & Sons Ltd: Chichester, England, 1990.Google Scholar
  16. 16.
    A. Galli and A. Zama, “Untersuchungen über die wahrnehmung ebener geometrischen figuren die ganz oder teilweise von anderen geometrischen figuren verdeckt sind,” Zeitschrift für Psychologie, Vol. 123, pp. 308–348, 1931.Google Scholar
  17. 17.
    F. Heitger and R. von der Heydt, “A computational model of neural contour processing: figure-ground segregation and illusory contours. in Proc. of the Fourth ICCV, 1993, IEEE Comp. Society, pp. 32–40.Google Scholar
  18. 18.
    G. Kanizsa, Organisation in Vision, Praeger: New York, 1979.Google Scholar
  19. 19.
    J. Koenderink, Solid Shape. MIT Press: Cambridge, MA, 1990.Google Scholar
  20. 20.
    A.N. Kolmogorov, “Three approaches to the quantitative definition of information,” Problems Inform. Transmission, Vol. 1, No. 1, pp. 1–7, 1965.Google Scholar
  21. 21.
    A.N. Kolmogorov, “Information theory and theory of algorithms,” in Selected Works, Y.V. Prokhorov and A.N. Shiryaev (Eds.), Vol. 3, Nauka (in Russian), 1987.Google Scholar
  22. 22.
    F Leymarie and M.D. Levine, “Fast raster scan distance propagation on the discrete rectangular lattice,” CVGIP: Image Understanding, Vol. 55, pp. 84–94, 1992.Google Scholar
  23. 23.
    T. Lindeberg, “On scale selection for differential operators,” in Proc. of the 8th Scand. Conf. on Im. Anal., Tromsø, Norway, 1993, pp. 857–866.Google Scholar
  24. 24.
    M. Lindenbaum and A. Berengolts, “A probabilistic interpretation of the saliency network,” in Proc.ECCV, 2000, pp. 257–272.Google Scholar
  25. 25.
    J.V. Mahoney, “Image chunking: Defining spatial building blocks for scene analysis,” MIT Artificial Intelligence Laboratory, MIT, Cambridge, MA, Technical Report 980, 1987.Google Scholar
  26. 26.
    B.B. Mandelbrot, “How long is the coast of Britain?,” Physica Scripta, Vol. 32, pp. 257–260, 1970.Google Scholar
  27. 27.
    B.B. Mandelbrot, The Fractal Geometry of Nature. Freeman: San Francisco, 1982.Google Scholar
  28. 28.
    G. Matheron, Random Sets and Integral Geometry. John Wiley and Sons: New York, 1975.Google Scholar
  29. 29.
    M. Mendès-France, “Dimension and entropy of regular curves,” in Fractals: Non-integral Dimensions and Applications, G. Cherbit (Ed.), John Wiley and Sons Ltd, Baffins Lane, Chichester, 1991a, pp. 222–230.Google Scholar
  30. 30.
    M. Mendès-France, “The Planck constant of a curve,” in Fractal Geometry and Analysis, S. Dubuc and J. Bélair, (Eds.), Kluwer Academic Publishers, 1991b, pp. 325–366.Google Scholar
  31. 31.
    H.R. Pagels, The Dreams of Reason: The Computer and the Rise of the Sciences of Complexity. Simon and Schuster: New York, 1988.Google Scholar
  32. 32.
    A.P. Pentland, “Fractal-based description of natural scenes,” IEEE Trans. Pattern Anal. Machine Intell.,Vol. 6, No. 6, pp. 661–674, 1984.Google Scholar
  33. 33.
    A.P. Pentland, “On describing complex surface shapes,” Image and Vision Computing, Vol. 3, No. 4, pp. 153–162, 1985.Google Scholar
  34. 34.
    L.A. Santaló, Integral Geometry and Geometric Probability. Vol. 1 of Encyclopedia of Mathematics and its Applications, Addison-Wesley Publishing Company: Reading, MA, 1976.Google Scholar
  35. 35.
    J. Serra, Image Analysis and Mathematical Morphology, Academic Press: London, 1982.Google Scholar
  36. 36.
    A. Sha'ashua, and S. Ullman, “Structural saliency: The detection of globally salient structures using a locally connected network,” in Proc. of the 2nd ICCV, 1988, IEEE Comp. Society: pp. 321–327.Google Scholar
  37. 37.
    A. Treisman, “Preattentive processes in vision,” Computer Vision, Graphics and Image Processing, Vol. 31, pp. 156–177, 1985.Google Scholar
  38. 38.
    C.Tricot, Curves andFractal Dimension, Springler-Verlag: New York, 1995.Google Scholar
  39. 39.
    C. Tricot, J.-F. Quiniou, D. Wehbi, C. Roques-Carmes, and B. Dubuc, “Evaluation de la dimension fractale d'un graphe,” Revue Phys. Appl., Vol. 23, pp. 111–124, 1988.Google Scholar
  40. 40.
    A. Turing, “On computable numbers with an application to the entscheidungsproblem,” Proc. London Math. Soc., Vol. 42, pp. 230–265, 1936, Correction, ibid, Vol. 43, pp. 544-546, 1937.Google Scholar
  41. 41.
    S. Ullman, “Three-dimensional object recognition,” in Cold Spring Harbor Symposia on Quantitative Biology, 1990,Vol. LV, Cold Spring Harbor Laboratory Press, pp. 889–898.Google Scholar
  42. 42.
    G. Valiron, Théorie des Fonctions. Masson et Cie: Paris, 1966.Google Scholar
  43. 43.
    L.Williams, and K. Thornber, “Acomparison of measures for detecting natural shapes in cluttered backgrounds,” in Proc. ECCV, 1998, pp. 432–448.Google Scholar

Copyright information

© Kluwer Academic Publishers 2001

Authors and Affiliations

  • Benoit Dubuc
    • 1
  • Steven W. Zucker
    • 2
  1. 1.Espace CourbeCanada
  2. 2.Center for Computational Vision and Control, Departments of Computer Science and Electrical EngineeringYale University New HavenCTUSA

Personalised recommendations