Advertisement

Computing contour closure

  • James H. Elder
  • Steven W. Zucker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1064)

Abstract

Existing methods for grouping edges on the basis of local smoothness measures fail to compute complete contours in natural images: it appears that a stronger global constraint is required. Motivated by growing evidence that the human visual system exploits contour closure for the purposes of perceptual grouping [6, 7, 14, 15, 25], we present an algorithm for computing highly closed bounding contours from images. Unlike previous algorithms [11, 18, 26], no restrictions are placed on the type of structure bounded or its shape. Contours are represented locally by tangent vectors, augmented by image intensity estimates. A Bayesian model is developed for the likelihood that two tangent vectors form contiguous components of the same contour. Based on this model, a sparsely-connected graph is constructed, and the problem of computing closed contours is posed as the computation of shortest-path cycles in this graph. We show that simple tangent cycles can be efficiently computed in natural images containing many local ambiguities, and that these cycles generally correspond to bounding contours in the image. These closure computations can potentially complement region-grouping methods by extending the class of structures segmented to include heterogeneous structures.

Keywords

Perceptual Organization Perceptual Grouping Contour Closure Local Edge Closure Computation 
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.
    T.D. Alter. The Role of Saliency and Error Propagation in Visual Object Recognition. PhD thesis, MIT, 1995.Google Scholar
  2. 2.
    I.J. Cox, J.M. Rehg, and S. Hingorani. A Bayesian multiple-hypothesis approach to edge grouping and contour segmentation. Int. J. Comp. Vision, 11(1):5–24, 1993.Google Scholar
  3. 3.
    M.P. do Carmo. Differential Geometry of Curves and Surfaces. Prentice-Hall, Englewood Cliffs, NJ, 1976.Google Scholar
  4. 4.
    G. Dudek and J.K. Tsotsos. Recognizing planar curves using curvature-tuned smoothing. In Proc. 10th Int. Conf. on Pattern Recogn., Atlantic City, 1990.Google Scholar
  5. 5.
    J. Elder. The visual computation of bounding contours. PhD thesis, McGill University, Dept. of Electrical Engineering, 1995.Google Scholar
  6. 6.
    J. Elder and S. W. Zucker. A measure of closure. Vision Research, 34(24):3361–3370, 1994.Google Scholar
  7. 7.
    J. Elder and S.W. Zucker. The effect of contour closure on the rapid discrimination of two-dimensional shapes. Vision Research, 33(7):981–991, 1993.Google Scholar
  8. 8.
    J. Elder and S.W. Zucker. Boundaries, textures and the perceptual binding of fragmented figures. In European Conf. on Visual Perception. Tubingen, Germany, 1995.Google Scholar
  9. 9.
    J. Elder and S.W. Zucker. Local scale control for edge detection and blur estimation. In Lecture Notes in Computer Science, New York, 1996. Proc. 4th European Conf. on Computer Vision, Springer Verlag.Google Scholar
  10. 10.
    W.T. Freeman. Steerable Filters and Local Analysis of Image Structure. PhD thesis, MIT Media Lab, 1992.Google Scholar
  11. 11.
    D.W. Jacobs. Finding salient convex groups. In I.J. Cox, P. Hansen, and B. Julesz, editors, Partitioning Data Sets, volume 19 of DIMACS (Series in Discrete Mathematics and Theoretical Computer Science). 1995.Google Scholar
  12. 12.
    G. Kanizsa. Organization in Vision. Praeger, New York, 1979.Google Scholar
  13. 13.
    M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. Proc. 1st Int. Conf. Comp. Vision, pages 259–268, 1987.Google Scholar
  14. 14.
    K. Koffka. Principles of Gestalt Psychology. Harcourt, Brace & World, New York, 1935.Google Scholar
  15. 15.
    I. Kovacs and B. Julesz. A closed curve is much more than an incomplete one: Effect of closure in figure-ground discrimination. Proc. Natl. Acad. Sci. USA, 90:7495–7497, 1993.Google Scholar
  16. 16.
    Y.G. Leclerc. Constructing simple stable descriptions for image partitioning. Int. J. Computer Vision, 3:73–102, 1989.Google Scholar
  17. 17.
    D.G. Lowe. Organization of smooth image curves at multiple scales. Int. J. Comp. Vision, 3:119–130, 1989.Google Scholar
  18. 18.
    M. Nitzberg, D. Mumford, and T. Shiota. Filtering, segmentation and depth. Lecture Notes in Computer Science, 662, 1993.Google Scholar
  19. 19.
    P. Parent and S.W. Zucker. Trace inference, curvature consistency, and curve detection. IEEE Trans. Pattern Anal. Machine Intell., 11:823–839, 1989.Google Scholar
  20. 20.
    T. Pavlidis. Structural Pattern Recognition. Springer-Verlag, Berlin, 1977.Google Scholar
  21. 21.
    E.M. Riseman and M.A. Arbib. Computational techniques in the visual segmentation of static scenes. Comp. Graph. Image Proc., 6:221–276, 1977.Google Scholar
  22. 22.
    E. Saund. Symbolic construction of a 2-d scale-space image. IEEE Trans. Pattern Anal. Machine Intell., 12(8):817–830, 1990.Google Scholar
  23. 23.
    R. Sedgewick. Algorithms in C. Addison-Wesley, Reading, Mass., 1990.Google Scholar
  24. 24.
    A. Sha'ashua and S. Ullman. Structural saliency: The detection of globally salient structures using a locally connected network. In Proc. 2nd Int. Conf. on Computer Vision, pages 321–327, Tampa, Florida, 1988. IEEE Computer Soc. Press.Google Scholar
  25. 25.
    A. Treisman and S. Gormican. Feature analysis in early vision: Evidence from search asymmetries. Psychol. Rev., 95:15–48, 1988.Google Scholar
  26. 26.
    L.R. Williams. Perceptual completion of occluded surfaces. PhD thesis, University of Massachusetts, Amherst, Mass., February 1994.Google Scholar
  27. 27.
    A. Yuille and P. Hallinan. Deformable templates. In A. Blake and A. Yuille, editors, Active Vision. MIT Press, Cambridge, Mass., 1992.Google Scholar
  28. 28.
    S.W. Zucker. The diversity of perceptual grouping. In M. Arbib and A. Hanson, editors, Vision, Brain and Cooperative Computation, pages 231–261. MIT, Cambridge, Mass., 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • James H. Elder
    • 1
  • Steven W. Zucker
    • 2
  1. 1.NEC Research InstitutePrincetonUSA
  2. 2.Centre for Intelligent MachinesMcGill UniversityMontréalCanada

Personalised recommendations