|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| Alexander Berengolts, Michael Lindenbaum, "On the Distribution of Saliency," 2012 IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 543-549, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 2, 2004. | |||
| BibTex | x | ||
| @article{ 10.1109/CVPR.2004.179, author = {Alexander Berengolts and Michael Lindenbaum}, title = {On the Distribution of Saliency}, journal ={2012 IEEE Conference on Computer Vision and Pattern Recognition}, volume = {2}, year = {2004}, issn = {1063-6919}, pages = {543-549}, doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2004.179}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - 2012 IEEE Conference on Computer Vision and Pattern Recognition TI - On the Distribution of Saliency SN - 1063-6919 SP543 EP549 A1 - Alexander Berengolts, A1 - Michael Lindenbaum, PY - 2004 KW - null VL - 2 JA - 2012 IEEE Conference on Computer Vision and Pattern Recognition ER - | |||
The calculation of salient structures is one of the early and basic ideas of perceptual organization in Computer Vision. Saliency algorithms typically mark edge-points with some saliency measure, growing with the length and the smoothness of the curve on which this edge-point lies. We consider a generalization [10] of the Ullman-Shaashua saliency measure [13] and aim to analyze the saliency measure in a probabilistic context: regarding the basic grouping information (grouping cues) as random variables, we use ergodicity and asymptotic analysis to derive the saliency distribution associated with the main curves ("figure") and with the rest of the image ("background"). We further consider finite-length curves and analyze their saliency values.
We observed several discrepancies between the observed distributions and the predictions we supply, discuss their sources and propose a way to account for them. Then, based on the derived distributions we show how to set threshold on the saliency for deciding optimally between figure and background, how to choose cues which are usable for saliency, and how to estimate bounds on the saliency performance.