A comparison of measures for detecting natural shapes in cluttered backgrounds
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.
KeywordsDirected Edge Saliency Function Affinity Function Illusory Contour Oriented Edge
Unable to display preview. Download preview PDF.
- 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
- 4.Horn, B.K.P., The Curve of Least Energy, MIT AI Lab Memo No. 612, MIT, Cambridge, Mass., 1981.Google Scholar
- 7.Mumford, D., Elastica and Computer Vision, Algebraic Geometry and Its Applications, Chandrajit Bajaj (ed.), Springer-Verlag, New York, 1994.Google Scholar
- 8.Press, W.H., Flannery, B.P., Teukolsky, S.A., and W.T. Vetterling, Numerical Recipes in C, Cambridge University Press, 1988.Google Scholar
- 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.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.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
- 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.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.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