This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
On the Distribution of Saliency
December 2006 (vol. 28 no. 12)
pp. 1973-1990
Detecting salient structures is a basic task in perceptual organization. Saliency algorithms typically mark edge-points with some saliency measure, which grows with the length and smoothness of the curve on which these edge-points lie. Here, we propose a modified saliency estimation mechanism that is based on probabilistically specified grouping cues and on curve length distributions. In this framework, the Shashua and Ullman saliency mechanism may be interpreted as a process for detecting the curve with maximal expected length. Generalized types of saliency naturally follow. We propose several specific generalizations (e.g., gray-level-based saliency) and rigorously derive the limitations on generalized saliency types. We then carry out a probabilistic analysis of expected length saliencies. Using ergodicity and asymptotic analysis, we derive the saliency distributions associated with the main curves and with the rest of the image. We then extend this analysis to finite-length curves. Using the derived distributions, we derive the optimal threshold on the saliency for discriminating between figure and background and bound the saliency-based figure-from-ground performance.

[1] M. Wertheimer, “Untersuchungen zur Lehre von der Gestalt. ii,” Psychologische Forschung, vol. 4, pp. 301-350, 1923, abridged English translation, Laws of Organization in Perceptual Forms, pp.331-363, 1938.
[2] S. Palmer, Vision Science—Photons to Phenomenology. MIT Press, 1999.
[3] U. Neisser, Cognitive Psychology. New York: Appleton-Century-Crofts, 1967.
[4] A. Treisman and G. Gelade, “A Feature Integration Theory of Attention,” Cognitive Psychology, vol. 12, pp. 97-136, 1980.
[5] C. Koch and S. Ullman, “Shifts in Selective Visual Attention: Towards the Underlying Neural Circuitry,” Human Neurobiology, vol. 4, pp. 219-227, 1985.
[6] J. Tsotsos, S. Culhane, W. Wai, Y. Lai, N. Davis, and F. Nuflo, “Modeling Visual Attention via Selective Tuning,” Artificial Intelligence, vol. 78, nos. 1-2, pp. 507-545, 1995.
[7] D. Marr, Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. W.H. Freeman and Company, 1982.
[8] A. Sha'ashua and S. Ullman, “Structural Saliency: The Detection of Globally Salient Structures Using Locally Connected Network,” Proc. Int'l Conf. Computer Vision (ICCV '88), pp. 321-327, 1988.
[9] U. Montanari, “On the Optimal Detection of Curves in Noisy Pictures. ” Comm. ACM, vol. 14, pp. 335-345, 1971.
[10] T. Alter and R. Basri, “Extracting Salient Curves from Images: An Analysis of the Saliency Network,” Int'l J. Computer Vision, vol. 27, pp. 51-69, 1998.
[11] G. Guy and G. Medioni, “Inferring Global Perceptual Contours from Local Features,” Int'l J. Computer Vision, vol. 20, nos. 1-2, pp.113-33, Oct. 1996.
[12] L. Williams and D. Jacobs, “Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience,” Proc. Int'l Conf. Computer Vision (ICCV '95), pp. 408-415, 1995.
[13] S. Sarkar and K. Boyer, “Quantitative Measures of Change Based on Feature Organization: Eigenvalues and Eigenvectors,” Proc. Conf. Computer Vision and Pattern Recognition (CVPR '96), pp. 478-483, 1996.
[14] L.R. Williams and K.K. Thornber, “A Comparison of Measures for Detecting Natural Shapes In Cluttered Backgrounds,” Proc. European Conf. Computer Vision, pp. 432-448, 1998.
[15] L. Herault and R. Horaud, “Figure-Ground Discrimination by Mean Field Annealing,” Proc. European Conf. Computer Vision (ECCV '92), pp. 58-66, 1992.
[16] A. Amir and M. Lindenbaum, “Ground from Figure Discrimination,” Computer Vision and Image Understanding, vol. 76, no. 1, pp.7-18, Oct. 1999.
[17] P. Parent and S. Zucker, “Trace Inference, Curvature Consistency, and Curve Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 8, pp. 823-839, Aug. 1989.
[18] E. Sharon, A. Brandt, and R. Basri, “Fast Multiscale Image Segmentation,” Proc. Conf. Computer Vision and Pattern Recognition (CVPR '00), pp. 70-77, 2000.
[19] I. Jermyn and H. Ishikawa, “Globally Optimal Regions and Boundaries as Minimum Ratio Weight Cycles,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1075-1088, Oct. 2001.
[20] E. Saund, “Perceptual Organization of Occluding Contours of Opaque Surfaces,” Computer Vision and Image Understanding, vol. 76, no. 1, pp. 70-82, Oct. 1999.
[21] X. Ren, C. Fowlkes, and J. Malik, “Scale-Invariant Contour Completion Using Conditional Random Fields,” Proc. Int'l Conf. Computer Vision (ICCV '05), vol. 2, pp. 1214-1221, 2005.
[22] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp.679-698, 1986.
[23] B. Dubuc and S. Zucker, “Complexity, Confusion, and Perceptual Grouping. Part II: Mapping Complexity,” Int'l J. Computer Vision, vol. 42, nos. 1/2, pp. 83-115, 2001.
[24] D.R. Martin, C.C. Fowlkes, and J. Malik, “Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp. 1-20, 2004.
[25] R. Golubchyck and M. Lindenbaum, “Improving the Saliency Algorithm by Cue Optimization,” Technical Report MSC-2006-07, Technion, 2006.
[26] J. Elder and S.W. Zucker, “Computing Contour Closure,” Proc. European Conf. Computer Vision (ECCV '96), vol. 1, pp. 399-412, 1996.
[27] A. Amir and M. Lindenbaum, “A Generic Grouping Algorithm and Its Quantitative Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 168-185, Feb. 1998.
[28] A. Berengolts and M. Lindenbaum, “On the Performance of Connected Components Grouping,” Int'l J. Computer Vision, vol. 41, no. 3, pp. 195-216, 2001.
[29] J. Elder and R.M. Goldberg, “Ecological Statistics of Gestalt Laws for the Perceptual Organization of Contours,” J. Vision, vol. 2, no. 4, pp. 324-353, 2002.
[30] M. Lindenbaum and A. Berengolts, “A Probabilistic Interpretation of the Saliency Network,” Proc. European Conf. Computer Vision (ECCV '00), pp. 257-272, 2000.
[31] A. Berengolts and M. Lindenbaum, “On the Distribution of Saliency,” Proc. Conf. Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 543-549, 2004.
[32] A. Berengolts and M. Lindenbaum, “On the Distribution of Saliency,” Technical Report CIS-2004-03, Technion, 2004.
[33] D.G. Lowe, Perceptual Organization and Visual Recognition. Kluwer Academic, 1985.
[34] A.P. Witkin and J.M. Tenenbaum, “On the Role of Structure in Vision,” Human and Machine Vision, pp. 481-543, Feb. 1983.
[35] S. Sarkar and K.L. Boyer, “Perceptual Organization in Computer Vision: A Review and Proposal for a Classifactory Structure,” IEEE Trans. Systems, Man, and Cybernetics, vol. 23, no. 2, pp. 382-399, Mar./Apr. 1993.
[36] A. Stuart and K. Ord, Kendall's Advanced Theory of Statistics, vol. 1. Arnold Press, 2003.
[37] F. Edgeworth, “The Law of Error,” Trans. Cambridge Philosophical Soc., vol. 20, pp. 36-113, 1904.
[38] C. Charlier, “Applications [de la théorie des probabilityés] à l'astronomie,” Traité, 1931.
[39] K. Fukunaga, Introduction to Statistical Pattern Recognition, second ed. Academic Press, 1990.
[40] J. Shen and S. Castan, “An Optimal Linear Operator for Edge Detection,” Proc. Conf. Computer Vision and Pattern Recognition (CVPR '86), pp. 109-114, 1986.

Index Terms:
Saliency networks, grouping, perceptual organization, figure-from-ground.
Citation:
Alexander Berengolts, Michael Lindenbaum, "On the Distribution of Saliency," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 1973-1990, Dec. 2006, doi:10.1109/TPAMI.2006.249
Usage of this product signifies your acceptance of the Terms of Use.