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.
Chapter PDF
Keywords
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
T.D. Alter. The Role of Saliency and Error Propagation in Visual Object Recognition. PhD thesis, MIT, 1995.
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.
M.P. do Carmo. Differential Geometry of Curves and Surfaces. Prentice-Hall, Englewood Cliffs, NJ, 1976.
G. Dudek and J.K. Tsotsos. Recognizing planar curves using curvature-tuned smoothing. In Proc. 10th Int. Conf. on Pattern Recogn., Atlantic City, 1990.
J. Elder. The visual computation of bounding contours. PhD thesis, McGill University, Dept. of Electrical Engineering, 1995.
J. Elder and S. W. Zucker. A measure of closure. Vision Research, 34(24):3361–3370, 1994.
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.
J. Elder and S.W. Zucker. Boundaries, textures and the perceptual binding of fragmented figures. In European Conf. on Visual Perception. Tubingen, Germany, 1995.
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.
W.T. Freeman. Steerable Filters and Local Analysis of Image Structure. PhD thesis, MIT Media Lab, 1992.
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.
G. Kanizsa. Organization in Vision. Praeger, New York, 1979.
M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. Proc. 1st Int. Conf. Comp. Vision, pages 259–268, 1987.
K. Koffka. Principles of Gestalt Psychology. Harcourt, Brace & World, New York, 1935.
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.
Y.G. Leclerc. Constructing simple stable descriptions for image partitioning. Int. J. Computer Vision, 3:73–102, 1989.
D.G. Lowe. Organization of smooth image curves at multiple scales. Int. J. Comp. Vision, 3:119–130, 1989.
M. Nitzberg, D. Mumford, and T. Shiota. Filtering, segmentation and depth. Lecture Notes in Computer Science, 662, 1993.
P. Parent and S.W. Zucker. Trace inference, curvature consistency, and curve detection. IEEE Trans. Pattern Anal. Machine Intell., 11:823–839, 1989.
T. Pavlidis. Structural Pattern Recognition. Springer-Verlag, Berlin, 1977.
E.M. Riseman and M.A. Arbib. Computational techniques in the visual segmentation of static scenes. Comp. Graph. Image Proc., 6:221–276, 1977.
E. Saund. Symbolic construction of a 2-d scale-space image. IEEE Trans. Pattern Anal. Machine Intell., 12(8):817–830, 1990.
R. Sedgewick. Algorithms in C. Addison-Wesley, Reading, Mass., 1990.
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.
A. Treisman and S. Gormican. Feature analysis in early vision: Evidence from search asymmetries. Psychol. Rev., 95:15–48, 1988.
L.R. Williams. Perceptual completion of occluded surfaces. PhD thesis, University of Massachusetts, Amherst, Mass., February 1994.
A. Yuille and P. Hallinan. Deformable templates. In A. Blake and A. Yuille, editors, Active Vision. MIT Press, Cambridge, Mass., 1992.
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.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Elder, J.H., Zucker, S.W. (1996). Computing contour closure. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015553
Download citation
DOI: https://doi.org/10.1007/BFb0015553
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive