Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition

EMMCVPR 1997: Energy Minimization Methods in Computer Vision and Pattern Recognition pp 19–34Cite as

Characterizing the distribution of completion shapes with corners using a mixture of random processes

  • Contours and Deformable Models
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1223))

Abstract

We derive an analytic expression for the distribution of contours x(t) generated by fluctuations in x(t) = ∂x.(t)/∂t due to stochastic impulses of two limiting types. The first type are frequent but weak while the second are infrequent but strong. The result has applications in computational theories of figurai completion and illusory contours because it can be used to model the prior probability distribution of short, smooth completion shapes punctuated by occasional discontinuities in orientation (i.e., corners). This work extends our previous work on characterizing the distribution of completion shapes which dealt only with the case of frequently acting weak impulses.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Belheumer, P.N., Bayesian Models for Reconstructing the Scene Geometry in a Pair of Stereo Images, Proc. Conf. Information Sciences and Systems, Johns Hopkins University, Baltimore, MD, 1993.

    Google Scholar 

  2. Blake, A., The Least Disturbance Principle and Weak Constraints, Pattern Recognition Letters 1, pp. 393–399, 1983.

    Google Scholar 

  3. Bruckstein, A.M. and Netravali, A.N., On Minimal Energy Trajectories, Computer Vision, Graphics and Image Processing 49, pp. 283–296, 1990.

    Google Scholar 

  4. Cox, I.J. Rehg, J.M. and Hingorani, S., A Bayesian Multiple Hypothesis Approach to Edge Grouping and Contour Segmentation, Intl. Journal of Computer Vision 11, pp. 5–24, 1993.

    Google Scholar 

  5. Feynman, R.P. and A.R. Hibbs, Quantum Mechanics and Path Integrals, New York, McGraw Hill, 1965.

    Google Scholar 

  6. Geman, S. and D. Geman, Stochastic Relaxation, Gibbs Distributions, and Bayesian Restoration of Images, IEEE Trans. Pattern Analysis and Machine Intelligence 6, pp. 721–741, 1984.

    Google Scholar 

  7. Grimson, W.E.L., and Pavlidis, T., Discontinuity Detection for Visual Surface Reconstruction, Computer Vision, Graphics and Image Processing 30, pp. 316–330, 1985.

    Google Scholar 

  8. Heitger, R. and von der Heydt, R., A Computational Model of Neural Contour Processing, Figure-ground and Illusory Contours, Proc. of 4th Intl. Conf. on Computer Vision, Berlin, Germany, 1993.

    Google Scholar 

  9. Horn, B.K.P., The Curve of Least Energy, MIT AI Lab Memo No. 612, MIT, Cambridge, Mass., 1981.

    Google Scholar 

  10. Kanizsa, G., Organization in Vision, Praeger, New York, 1979.

    Google Scholar 

  11. Kass, M., Witkin, A. and Terzopolous, D., Snakes: Active Minimum Energy Seeking Contours, Proc. of the First Intl. Conf. on Computer Vision (ICCV), London, England, pp. 259–268, 1987.

    Google Scholar 

  12. Marroquin, J., Surface Reconstruction Preserving Discontinuities, MIT AI Lab Memo No. 792, MIT, Cambridge, MA, 1984.

    Google Scholar 

  13. Mumford, D., Elastica and Computer Vision, Algebraic Geometry and Its Applications, Chandrajit Bajaj (ed.), Springer-Verlag, New York, 1994.

    Google Scholar 

  14. Mumford, D. and Shah, J., Boundary Detection by Minimizing Functionals, Proc. IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR), 1985.

    Google Scholar 

  15. Terzopolous, D., Computing Visible Surface Representations, MIT AI Lab Memo No. 612, MIT, Cambridge, MA, 1985.

    Google Scholar 

  16. Thornber, K.K., Treatment of Microscopic Fluctuations in Noise Theory, BSTJ 53, pp. 1041–1078, 1974.

    Google Scholar 

  17. Thornber, K.K., A New Approach for Treating Fluctuations in Noise Theory, J. Appl. Phys. 46, pp. 2781–2787, 1975.

    Google Scholar 

  18. Thornber, K.K., Application of Scaling to Problems in High Field Electronic Transport, J. Appl. Phys. 52, pp. 279–290, 1981.

    Google Scholar 

  19. Thornber, K.K. and L.R. Williams, Analytic Solution of Stochastic Completion Fields, Biological Cybernetics 75, pp. 141–151, 1996.

    Google Scholar 

  20. Williams, L.R., and D.W. Jacobs, Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience, Neural Computation 9 (in press).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. NEC Research Institute, 4 Independence Way, 08540, Princeton, NJ, USA

    K. K. Thornber & L. R. Williams

Authors
  1. K. K. Thornber
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. L. R. Williams
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Marcello Pelillo Edwin R. Hancock

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Thornber, K.K., Williams, L.R. (1997). Characterizing the distribution of completion shapes with corners using a mixture of random processes. In: Pelillo, M., Hancock, E.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1997. Lecture Notes in Computer Science, vol 1223. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62909-2_70

Download citation

  • DOI: https://doi.org/10.1007/3-540-62909-2_70

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-62909-2

  • Online ISBN: 978-3-540-69042-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation