DocumentCode
2627720
Title
Visual organization for figure/ground separation
Author
Geiger, Davi ; Kumaran, Krishnan ; Parida, Laxmi
Author_Institution
Courant Inst. of Math. Sci., New York, NY, USA
fYear
1996
fDate
18-20 Jun 1996
Firstpage
155
Lastpage
160
Abstract
A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work, we have shown we could diffuse a proper set of junction hypothesis (what is salient or background) to obtain a surface where their boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We address the problem of selecting the best image organization (set of hypothesis). We propose an optimization criteria based on a coherence measure between pairs of junctions (correlation between the diffusion of each pair). A statistical physics approach to select the best organization is applied. The experiments suggest that despite the large number of possible organizations our approach may take only a few steps (in organization space) to select the best one
Keywords
computer vision; image reconstruction; coherence measure; figure/ground separation; illusory contour figures; junction hypothesis; optimization criteria; visual organization; Bayesian methods; Coherence; Entropy; Feature extraction; Jacobian matrices; Labeling; Physics; Shape;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference on
Conference_Location
San Francisco, CA
ISSN
1063-6919
Print_ISBN
0-8186-7259-5
Type
conf
DOI
10.1109/CVPR.1996.517068
Filename
517068
Link To Document