Abstract | ||
---|---|---|
We propose a mid-level image segmentation framework that combines multiple
figure-ground hypothesis (FG) constrained at different locations and scales,
into interpretations that tile the entire image. The problem is cast as
optimization over sets of maximal cliques sampled from the graph connecting
non-overlapping, putative figure-ground segment hypotheses. Potential functions
over cliques combine unary Gestalt-based figure quality scores and pairwise
compatibilities among spatially neighboring segments, constrained by
T-junctions and the boundary interface statistics resulting from projections of
real 3d scenes. Learning the model parameters is formulated as rank
optimization, alternating between sampling image tilings and optimizing their
potential function parameters. State of the art results are reported on both
the Berkeley and the VOC2009 segmentation dataset, where a 28% improvement was
achieved. |
Year | Venue | Keywords |
---|---|---|
2010 | Clinical Orthopaedics and Related Research | image segmentation,cumulant,pattern recognition,graph connectivity |
Field | DocType | Volume |
Pairwise comparison,Scale-space segmentation,Pattern recognition,Unary operation,Ranking,Segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Sampling (statistics),Artificial intelligence,Machine learning | Journal | abs/1009.4 |
Citations | PageRank | References |
6 | 0.99 | 17 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
João Carreira | 1 | 1680 | 108.75 |
Adrian Ion | 2 | 222 | 21.11 |
Cristian Sminchisescu | 3 | 3700 | 244.41 |