The Role of Propagation and Medial Geometry in Human Vision

  • Benjamin Kimia
  • Amir Tamrakar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2525)


A key challenge underlying theories of vision is how the spatially restricted, retinotopically represented feature computations can be integrated to form abstract, coordinate-free object models. A resolution likely depends on the use of intermediate-level representations which can on the one hand be populated by local features and on the other hand be used as atomic units underlying the formation of, and interaction with, object hypotheses. The precise structure of this intermediate representation derives from the varied requirements of a range of visual tasks, which motivate a significant role for incorporating a geometry of visual form. The need to integrate input from features capturing surface properties such as texture, shading, motion, color, etc., as well as from features capturing surface discontinuities such as silhouettes, T-junctions, etc., implies a geometry which captures both regional and boundary aspects. Curves, as a geometric model of boundaries, have been extensively and explicitly used as an intermediate representation in computational, perceptual, and physiological studies. However, the medial axis which has been popular in computer vision as a geometric regionbased model of the interior of closed boundaries, has not been explicitly used as an intermediate representation.We present a unified theory of perceptual grouping and object recognition where the intermediate representation is a visual fragment which itself is based on the medial axis. Through various sequences of transformations of the medial axis representation, visual fragments are grouped in various configurations to form object hypotheses, and are related to stored models. The mechanisms underlying both the computation and the transformation of the medial axis is a lateral wave propagation model. Recent psychophysical experiments depicting contrast sensitivity map peaks at the medial axes of stimuli, and experiments on perceptual filling-in, and brightness induction and modulation, are consistent with both the use of a medial axis representation and a propagationbased scheme. Also, recent neurophysiological recordings in V1 correlate with the medial axis hypothesis and a horizontal propagation scheme. This evidence supports a geometric computational paradigm for processing sensory data where both dynamic in-plane propagation and feedforward-feedback connections play an integral role.


Object Recognition Vision Research Medial Axis Perceptual Grouping Intermediate Representation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    I. Biederman. Recognition-by-components: A theory of human image understanding. Psychological Review, 94:115–147, 1987.CrossRefGoogle Scholar
  2. 2.
    H. Blum. Biological shape and visual science. J. Theor. Biol., 38:205–287, 1973.CrossRefGoogle Scholar
  3. 3.
    V. Bringuier, F. Chavane, L. Glaeser, and Y. Fregnac. Horizontal propagation of visual activity in the synaptic integration field of area 17 neurons. Science, 283:695–699, January 1999.Google Scholar
  4. 4.
    R. Devalois, M. Webster, K. Devalois, and B. LingelBach. Temporal properties of brightness and color induction. Vision Research, 26:887–897, 1986.CrossRefGoogle Scholar
  5. 5.
    D. V. Essen, C. Anderson, and D. Felleman. Information processing in the primate visual system: An integrated systems perspective. Science, 255(5043):419–423, 1992.CrossRefGoogle Scholar
  6. 6.
    B. Gibson and M. Peterson. Does orientation-independent object recognition precede orientation-dependent recognition? Evidence from a cueing paradigm. Journal of Experimental Psychology: Human Perception and Performance, 20:299–316, 1994.CrossRefGoogle Scholar
  7. 7.
    C. D. Gilbert and T. N. Wiesel. Clustered intrinsic connections in cat visual cortex. Journal of Neuroscience, 3:1116–1133, 1983.Google Scholar
  8. 8.
    A. Grinvald, E. Lieke, R. Frostig, and R. Hildesheim. Cortical point-spread function longrange lateral iteraction revealed by real-time optical imaging of macaque monkey primary visual cortex. J. Neuroscience, 14:2545–2568, 1994.Google Scholar
  9. 9.
    M. S. Johannes, T. B. Sebastian, H. Tek, and B. B. Kimia. Perceptual organization as object recognition divided by two. In Workshop on Perceptual Organization in Computer Vision, pages 41–46, 2001.Google Scholar
  10. 10.
    Z. Kisvarday and U. Eysel. Functional and structural topography of horizontal inhibitory connections in cat visual cortex. European Journal of Neuroscience, 5:1558–72, 1993.CrossRefGoogle Scholar
  11. 11.
    I. Kovacs, A. Feher, and B. Julesz. Medial-point description of shape: a representation for action coding and its psychophysical correlates. Vision Research, 38:2323–2333, 1998.CrossRefGoogle Scholar
  12. 12.
    I. Kovacs and B. Julesz. A closed curve is much more than an incomplete one: Effect of closure in figure-ground segmentation. PNAS, 90:7495–7497, August 1993.Google Scholar
  13. 13.
    V. Lamme. The neurophysiology of figure-ground segmentation. J. Neurosci, 15:1605–1615, 1995.Google Scholar
  14. 14.
    T. S. Lee, D. Mumford, R. Romero, and V. A. Lamme. The role of primary visual cortex in higher level vision. Vision Research, 38:2429–2454, 1998.CrossRefGoogle Scholar
  15. 15.
    D. Marr. Vision. W.H. Freeman, San Fransisco, 1982.Google Scholar
  16. 16.
    M. Paradiso and S. Hahn. Filling-in percepts produced by luminance modulation. Vision Research, 36:2657–2663, 1996.CrossRefGoogle Scholar
  17. 17.
    M. A. Paradiso and K. Nakayama. Brightness perception and filling in. Vision Research, 31:1221–36, 1991.CrossRefGoogle Scholar
  18. 18.
    A. Pentland. Automatic extraction of deformable part models. Intl. J. of Computer Vision, 4(2):107–126, March 1990.CrossRefGoogle Scholar
  19. 19.
    I. Rock. An introduction to Perception. MacMillan, 1975.Google Scholar
  20. 20.
    A. Rossi and M. Paradiso. Temporal limits of brightness induction and mechanisms of brightness perception. Vision Research, 36:1391–1398, 1996.CrossRefGoogle Scholar
  21. 21.
    M. Schmolesky, Y. Wang, D. Hanes, K. Thompson, S. Leutgeb, J. Schall, and A. Leventhal. Signal timing across the macaque visual system. Journal of Neurophysiology, 79(6):3272–8, 1998.Google Scholar
  22. 22.
    T. Sebastian, P. Klein, and B. Kimia. Recognition of shapes by editing their shock graphs. IEEE Trans. Pattern Analysis and Machine Intelligence, page Submitted, 2001.Google Scholar
  23. 23.
    T. B. Sebastian, P. N. Klein, and B. B. Kimia. Recognition of shapes by editing shock graphs. In Proceedings of the Eighth International Conference on Computer Vision, pages 755–762, Vancouver, Canada, July 9-12 2001. IEEE Computer Society Press.Google Scholar
  24. 24.
    T. B. Sebastian, P. N. Klein, and B. B. Kimia. Shock-based indexing into large shape databases. In Seventh European Conference on omputer Vision, pages Part III:731–746, Copenhagen, Denmark, May 28-31 2002. Springer Verlag.Google Scholar
  25. 25.
    W. Singer and C. Gray. Visual feature integration and the temporal correlation hypothesis. Annu. Rev. Neuro., 18:555–86, 1995.CrossRefGoogle Scholar
  26. 26.
    H. Tek and B. B. Kimia. Symmetry maps of free-form curve segments via wave propagation. In Proceedings of the Fifth International Conference on Computer Vision, pages 362–369, KerKyra, Greece, September 20-25 1999. IEEE Computer Society Press.Google Scholar
  27. 27.
    H. Tek and B. B. Kimia. Symmetry maps of free-form curve segments via wave propagation. Intl. J. of Computer Vision, page Accepted to appear, 2002.Google Scholar
  28. 28.
    D. Terzopoulos and D. Metaxas. Dynamic 3D models with local and global deformations: Deformable superquadrics. IEEE Trans. Pattern Analysis and Machine Intelligence, 13(7):703–714, July 1991.CrossRefGoogle Scholar
  29. 29.
    L. Williams and K. Thornber. A comparison of measures for detecting natural shapes in cluttered backgrounds. IJCV, 34(2-3):81–96, November 1999.CrossRefGoogle Scholar
  30. 30.
    S. C. Zhu and A. L. Yuille. FORMS:A flexible object recognition and modeling system. Intl. J. of Computer Vision, 20(3):187–212, 1996.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Benjamin Kimia
    • 1
  • Amir Tamrakar
    • 1
  1. 1.LEMSBrown UniversityProvidenceUSA

Personalised recommendations