A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics

  • Xiaofeng Ren
  • Jitendra Malik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2350)

Abstract

We derive a probabilistic multi-scale model for contour completion based on image statistics. The boundaries of human segmented images are used as “ground truth”. A probabilistic formulation of contours demands a prior model and a measurement model. From the image statistics of boundary contours, we derive both the prior model of contour shape and the local likelihood model of image measurements. We observe multi-scale phenomena in the data, and accordingly propose a higher-order Markov model over scales for the contour continuity prior. Various image cues derived from orientation energy are evaluated and incorporated into the measurement model. Based on these models, we have designed a multi-scale algorithm for contour completion, which exploits both contour continuity and texture. Experimental results are shown on a wide range of images.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    S. Belongie and J. Malik. Finding boundaries in natural images: A new method using point descriptors and area completion. In Proc. 5th Euro. Conf. Computer Vision, Freiburg, Germany, June 1998.Google Scholar
  2. 2.
    J.H. Elder and S.W. Zucker. Computing contour closures. In Proc. Euro. Conf. Computer Vision, volume I, pages 399–412, Cambridge, England, Apr 1996.Google Scholar
  3. 3.
    W. S. Geisler, J. S. Perry, B. J. Super, and D. P. Gallogly. Edge co-occurrence in natural images predicts contour grouping performance. Vision Research, 41:711–724, 2001.CrossRefGoogle Scholar
  4. 4.
    S. Geman and D. Geman. Stochastic relaxation, gibbs distribution, and the bayesian retoration of images. IEEE Trans. Pattern Analysis and Machine Intelligence, 6:721–41, Nov. 1984.Google Scholar
  5. 5.
    G. Guy and G. Medioni. Inferring global perceptual contours from local features. Int’l. Journal of Computer Vision, 20(1–2):113–33, Oct. 1996.Google Scholar
  6. 6.
    F. Heitger and R. von der Heydt. A computational model of neural contour processing. In Proc. Int. Conf. Computer Vision, pages 32–40, Berlin, Germany, May 1993.Google Scholar
  7. 7.
    J. Huang and D. Mumford. Statistics of natural images and models. In Proc. IEEE Conf. Comput. Vision and Pattern Recognition, pages I:541–547, 1999.Google Scholar
  8. 8.
    S. Konishi, A.L. Yuille, J.M. Coughlan, and S.C. Zhu. Fundamental bounds on edge detection: An information theoretic evaluation of different edge cues. pages I:573–579, 1999.Google Scholar
  9. 9.
    T. Leung and J. Malik. Contour continuity in region-based image segmentation. In H. Burkhardt and B. Neumann, editors, Proc. Euro. Conf. Computer Vision, volume 1, pages 544–59, Freiburg, Germany, June 1998. Springer-Verlag.Google Scholar
  10. 10.
    J. Malik, S. Belongie, T. Leung, and J. Shi. Contour and texture analysis for image segmentation. Int’l. Journal of Computer Vision, 43(1):7–27, June 2001.Google Scholar
  11. 11.
    D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. 8th Int’l. Conf. Computer Vision, volume 2, pages 416–423, July 2001.Google Scholar
  12. 12.
    M.C. Morrone and R.A. Owens. Feature detection from local energy. Pattern Recognition Letters, 6:303–13, 1987.CrossRefGoogle Scholar
  13. 13.
    D. Mumford. Elastica and computer vision. In Chandrajit Bajaj, editor, Algebraic Geometry and Its Applications, pages 491–506. Springer Verlag, 1994.Google Scholar
  14. 14.
    P. Parent and S.W. Zucker. Trace inference, curvature consistency, and curve detection. IEEE Trans. Pattern Analysis and Machine Intelligence, 11(8):823–39, Aug. 1989.Google Scholar
  15. 15.
    P. Perona and J. Malik. Boundary detection using quadratic filters: Performance criteria and experimental assessment. In SPIE, 1708.Google Scholar
  16. 16.
    P. Perona and J. Malik. Detecting and localizing edges composed of steps, peaks and roofs. In Proc. Int. Conf. Computer Vision, pages 52–7, Osaka, Japan, Dec 1990.Google Scholar
  17. 17.
    L. Rosenthaler, F. Heitger, O. Kubler, and R. von der Heydt. Detection of general edges and key-points. In Proc. 2nd Europ. Conf. Comput. Vision, G. Sandini (Ed.), LNCS-Series Vol. 588, Springer-Verlag, pages 78–86, 1992.Google Scholar
  18. 18.
    E. Sharon, A. Brandt, and R. Basri. Completion energies and scale. IEEE Trans. Pattern Analysis and Machine Intelligence, 22(10):1117–1131, October 2000.Google Scholar
  19. 19.
    J. Shi and J. Malik. Normalized cuts and image segmentation. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 731–7, San Juan, Puerto Rico, June 1997.Google Scholar
  20. 20.
    L. Williams, J. Zweck, T. Wang, and K. Thornber. Computing stochastic completion fields in linear-time using a resolution pyramid. CVIU, 76(3):289–297, December 1999.Google Scholar
  21. 21.
    L.R. Williams and D.W. Jacobs. Stochastic completion fields: a neural model of illusory contour shape and salience. In Proc. 5th Int. Conf. Computer Vision, pages 408–15, Cambridge, MA, June 1995.Google Scholar
  22. 22.
    S.C. Zhu. Embedding gestalt laws in markov random fields. IEEE Trans. Pattern Analysis and Machine Intelligence, 21(11):1170–1187, November 1999.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Xiaofeng Ren
    • 1
  • Jitendra Malik
    • 1
  1. 1.Computer Science DivisionUniversity of California at BerkeleyBerkeley

Personalised recommendations