On Computing Visual Flows with Boundaries: The Case of Shading and Edges

  • Ohad Ben-Shahar
  • Patrick S. Huggins
  • Steven W. Zucker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2525)


Many visual tasks depend upon the interpretation of visual structures that are flow fields, such as optical flow, oriented texture, and shading. The computation of these visual flows involves a delicate tradeo off: imaging imperfections lead to noisy and sparse initial flow measurements, necessitating further processing to infer dense coherent flows; this processing typically entails interpolation and smoothing, both of which are prone to destroy visual flow discontinuities. However, discontinuities in visual flows signal corresponding discontinuities in the physical world, thus it is critical to preserve them while processing the flow. In this paper we present a computational approach motivated by the architecture of primary visual cortex that directly incorporates boundary information into a flow relaxation network. The result is a robust computation of visual flows with the capacity to handle noisy or sparse data sets while providing stability along flow boundaries. We demonstrate the effectiveness of our approach by computing shading flows in images with intensity edges.


Primary Visual Cortex Computing Visual Line Discontinuity Gradient Ascent Visual Flow 
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.
    O. Ben-Shahar and S. Zucker. On the perceptual organization of texture and shading flows: From a geometrical model to coherence computation. In CVPR, pages 1048–1055, 2001.Google Scholar
  2. 2.
    O. Ben-Shahar and S. Zucker. The perceptual organization of texture flow: A contextual inference approach. IEEE PAMI., 2002. In press.Google Scholar
  3. 3.
    L. Borg-Graham, C. Monier, and Y. Fregnac. Visual input evokes transient and strong shunting inhibition in visual cortical neurons. Nature, 292:369–373, 1998.Google Scholar
  4. 4.
    P. Breton and S. Zucker. Shadows and shading flow fields. In CVPR, 1996.Google Scholar
  5. 5.
    J. Canny. A computational approach to edge detection. IEEE PAMI, 8(6):679–698, 1986.CrossRefGoogle Scholar
  6. 6.
    A. Dobbins, S. Zucker, and M. Cynader. Endstopped neurons in the visual cortex as a substrate for calculating curvature. Nature, 329(6138):438–441, 1987.CrossRefGoogle Scholar
  7. 7.
    J. Gibson. The Perception of the Visual World. The Riverside Press, 1950.Google Scholar
  8. 8.
    C. Gilbert. Horizontal integration and cortical dynamics. Neuron, 9:1–13, 1992.CrossRefGoogle Scholar
  9. 9.
    D. Hubel and T. Wiesel. Functional architecture of macaque monkey visual cortex. In Proc. R. Soc. London Ser. B, volume 198, pages 1–59, 1977.Google Scholar
  10. 10.
    P. Huggins and S. Zucker. Folds and cuts: how shading flows into edges. In ICCV, 2001.Google Scholar
  11. 11.
    R. Hummel and S. Zucker. On the foundations of the relaxation labeling proceeses. IEEE PAMI, 5:267–287, 1983.CrossRefzbMATHGoogle Scholar
  12. 12.
    L. Iverson and S. Zucker. Logical/linear operators for image curves. IEEE PAMI, 17(10):982–996, 1995.CrossRefGoogle Scholar
  13. 13.
    G. Kanizsa. Organization in Vision: Essays on Gestalt Perception. Praeger Publishers, 1979.Google Scholar
  14. 14.
    M. Kass and A. Witkin. Analyzing oriented patterns. CVGIP, 37:362–385, 1987.Google Scholar
  15. 15.
    B. O'Neill. Elementary Differential Geometry. Academic Press, 1966.Google Scholar
  16. 16.
    P. Parent and S. Zucker. Trace inference, curvature consistency, and curve detection. IEEE PAMI, 11(8):823–839, 1989.CrossRefGoogle Scholar
  17. 17.
    P. Perona. Orientation diffusion. IEEE Trans. Image Processing, 7(3), 1998.Google Scholar
  18. 18.
    A. Rao and R. Jain. Computerized flow field analysis: Oriented texture fields. IEEE PAMI, 17(7):693–709, 1992.CrossRefGoogle Scholar
  19. 19.
    K. Stevens. The line of curvature constraint and the interpretation of 3d shape from parallel surface contours. In Proc. IJCAI, pages 1057–1061, 1983.Google Scholar
  20. 20.
    B. Tang, G. Sapiro, and V. Caselles. Diffusion of general data on non-flat manifolds via harmonic maps theory: The direction diffusion case. IJCV, 36(2):149–161, 2000.CrossRefGoogle Scholar
  21. 21.
    J. Todd and F. Reichel. Visual perception of smoothly curved surfaces from doubleprojected contour patterns. J. Exp. Psych.: Human Perception and Performance, 16(3):665–674, 1990.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Ohad Ben-Shahar
    • 1
  • Patrick S. Huggins
    • 1
  • Steven W. Zucker
    • 1
  1. 1.Department of Computer Science and Interdisciplinary Neuroscience ProgramYale UniversityNew HavenUSA

Personalised recommendations