Image segmentation by figure-ground composition into maximal cliques

  • Authors:

  • Adrian Ion;Joao Carreira;Cristian Sminchisescu

  • Affiliations:

  • Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn, Germany;Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn, Germany;Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn, Germany

  • Venue:
  • ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

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.