Loading...
Please wait, while we are loading the content...
Similar Documents
Probabilistic joint image segmentation and labeling by figure-ground . . . (2013)
| Content Provider | CiteSeerX |
|---|---|
| Author | Ion, Adrian Carreira, J. Sminchisescu, Cristian |
| Description | We propose a layered statistical model for image segmentation and labeling obtained by cobining independently extracted, possibly overlapping sets of figure-ground segmentations (FG). The process of constructing consistent image segmentations, called tilings, is cast as optimization over sets of maximal cliques sampled from a graph connecting all non-overlapping figure-ground segment hypotheses. Potential functions over cliques combine unary, Gestalt-based figure qualities, and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics of real scenes. Building on the segmentation layer, we further derive a joint image segmentation and labeling model (JSL) which, given a bag of FGs, constructs a joint probability distribution over both the compatible image interpretations (tilings) composed from those segments, and over their labeling into categories. The process of drawing samples from the joint distribution can be interpreted as first sampling tilings, followed by sampling labelings, conditioned on the choice of a particular tiling. We learn the segmentation and labeling parameters jointly, based on Maximum Likelihood with a novel estimation procedure we refer to as incremental saddle-point approximation. The partition function over tilings In NIPS |
| File Format | |
| Language | English |
| Publisher Date | 2013-01-01 |
| Access Restriction | Open |
| Subject Keyword | Max-imal Clique Compatible Im-age Interpretation Layered Statistical Model Novel Estimation Procedure Maximum Likelihood Non-overlapping Figure-ground Segment Hypothesis Consistent Image Segmentation Sam-pling Labelings Boundary Interface Statistic Segmentation Layer Poten-tial Function Joint Probability Distribution Incremental Saddle-point Approximation Particular Tiling Real Scene Image Segmentation Gestalt-based Figure Quality Probabilistic Joint Image Segmentation Figure-ground Segmentation Partition Function Joint Image Segmentation Joint Distribution |
| Content Type | Text |
| Resource Type | Article |
