[Zurück]

A. Ion, J. Carreira, C. Sminchisescu:
"Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition";
Vortrag: ICCV 2013 Workshop: Inference for probabilistic graphical models (PGMs), Sydney, Australia; 02.12.2013; in: "ICCV 2013 Proceedings", Springer Science+Business Media New York 2013, New York (2013), S. 1 - 18.

We propose a layered statistical model for image
segmentation and labeling obtained by combining independently
extracted, possibly overlapping sets of figure-ground
(FG) segmentations. 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, Gestaltbased
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.

http://dx.doi.org/10.1007/s11263-013-0663-7