Image segmentation by figure-ground composition into maximal cliques Conference Paper


Author(s): Ion, Adrian; Carreira, Joao; Sminchisescu, Cristian
Title: Image segmentation by figure-ground composition into maximal cliques
Affiliation IST Austria
Abstract: We propose a mid-level statistical model for image segmentation that composes multiple figure-ground hypotheses (FG) obtained by applying constraints at different locations and scales, into larger interpretations (tilings) of the entire image. Inference 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. Learning the model parameters is based on maximum likelihood, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on the Berkeley and Stanford segmentation datasets, as well as VOC2009, where a 28% improvement was achieved.
Conference Title: ICCV: International Conference on Computer Vision
Conference Dates: November 6-13, 2011
Conference Location: Barcelona, Spain
Publisher: IEEE  
Date Published: 2011-01-01
Start Page: 2110
End Page: 2117
DOI: 10.1109/ICCV.2011.6126486
Open access: no
IST Austria Authors
  1. Adrian Ion
    4 Ion
Related IST Austria Work