A comparison of measures for detecting natural shapes in cluttered backgrounds

  • Lance R. Williams
  • Karvel K. Thornber
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)


We propose a new measure of perceptual saliency and quantitatively compare its ability to detect natural shapes in cluttered backgrounds to five previously proposed measures. As defined in the new measure, the saliency of an edge is the fraction of closed random walks which contain that edge. The transition probability matrix defining the random walk between edges is based on a distribution of natural shapes modeled by a stochastic motion. Each of the saliency measures in our comparison is a function of a set of affinity values assigned to pairs of edges. Although the authors of each measure define the affinity between a pair of edges somewhat differently, all incorporate the Gestalt principles of good-continuation and proximity in some form. In order to make the comparison meaningful, we use a single definition of affinity and focus instead on the performance of the different functions for combining affinity values. The primary performance criterion is accuracy. We compute false-positive rates in classifying edges as signal or noise for a large set of test figures. In almost every case, the new measure significantly outperforms previous measures.


Directed Edge Saliency Function Affinity Function Illusory Contour Oriented Edge 
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.
    Alter, T. and R. Basri, Extracting Salient Contours from Images: An Analysis of the Saliency Network, Proc. IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR '96), pp. 13–20, San Francisco, CA, 1996.Google Scholar
  2. 2.
    Grossberg, S., and E. Mingolla, Neural Dynamics of Form Perception: Boundary Completion, Illusory Figures, and Neon Color Spreading, Psychological Review 92, pp. 173–211, 1985.CrossRefGoogle Scholar
  3. 3.
    Guy, G. and G. Medioni, Inferring Global Perceptual Contours from Local Features, Intl. Journal of Computer Vision 20, pp. 113–133, 1996.CrossRefGoogle Scholar
  4. 4.
    Horn, B.K.P., The Curve of Least Energy, MIT AI Lab Memo No. 612, MIT, Cambridge, Mass., 1981.Google Scholar
  5. 5.
    Hérault, L. and R. Horaud, Figure-Ground Discrimination: A Combinatorial Optimization Approach, IEEE Trans. on Pattern Analysis and Machine Intelligence 15, pp. 899–914, 1993.CrossRefGoogle Scholar
  6. 6.
    Montanari, U., On the Optimal Detection of Curves in Noisy Pictures, Comm. of the Assoc. for Computing Machinery 14, pp. 335–345, 1971.zbMATHGoogle Scholar
  7. 7.
    Mumford, D., Elastica and Computer Vision, Algebraic Geometry and Its Applications, Chandrajit Bajaj (ed.), Springer-Verlag, New York, 1994.Google Scholar
  8. 8.
    Press, W.H., Flannery, B.P., Teukolsky, S.A., and W.T. Vetterling, Numerical Recipes in C, Cambridge University Press, 1988.Google Scholar
  9. 9.
    Rosenfeld, A., Hummel R., and S. Zucker, Scene Labeling by Relaxation Operations, IEEE Trans. on Systems Man and Cybernetics 6, pp. 420–433, 1976.zbMATHMathSciNetCrossRefGoogle Scholar
  10. 10.
    Sarkar, S. and K. Boyer, Quantitative Measures of Change based on Feature Organization: Eigenvalues and Eigenvectors, Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '96), pp. 478–483, San Francisco, CA, 1996.Google Scholar
  11. 11.
    Shashua, A. and S. Ullman, Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network, 2nd Intl. Conf. on Computer Vision, Clearwater, FL, 1988.Google Scholar
  12. 12.
    Sharon, E., Brandt, A., and R. Basri, Completion Energies and Scale, Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '97), pp. 884–890, San Juan, Puerto Rico, 1997.Google Scholar
  13. 13.
    Thornber, K.K. and L.R. Williams, Analytic Solution of Stochastic Completion Fields, Biological Cybernetics 75, pp. 141–151, 1996.zbMATHCrossRefGoogle Scholar
  14. 14.
    Ullman, S., Filling-in the Gaps: The Shape of Subjective Contours and a Model for Their Generation, Biological Cybernetics 21, pp. 1–6, 1976.MathSciNetCrossRefGoogle Scholar
  15. 15.
    Williams, L.R., Wang, T. and K.K. Thornber, Computing Stochastic Completion Fields in Linear-Time Using a Resolution Pyramid, Proc. of 7th Intl. Conf. on Computer Analysis of Images and Patterns (CAIP '97), Kiel, Germany, 1997.Google Scholar
  16. 16.
    Williams, L.R. and D.W. Jacobs, Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience, Neural Computation 9, pp. 849–870, 1997.Google Scholar
  17. 17.
    Yen, S. and L. Finkel, “Pop-Out” of Salient Contours in a Network Based on Striate Cortical Connectivity, Investigative Opthalmology and Visual Science (ARVO), Vol. 37, No. 3, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Lance R. Williams
    • 1
  • Karvel K. Thornber
    • 2
  1. 1.Dept. of Computer ScienceUniversity of New MexicoAlbuquerque
  2. 2.NEC Research InstitutePrinceton

Personalised recommendations