Tri-Map Self-Validation Based on Least Gibbs Energy for Foreground Segmentation

The Bayesian framework forms a solid foundation for image segmentation. With this as a basis, an image is modeled as a Markov random field (MRF) with observations incorporated with a given tri-map. Although MRF-based methods have proved successful in interactive or supervised foreground segmentation, high-quality segmentation can be obtained only when the tri-map is sufficiently discriminative. We argue that the least Gibbs energy can be formulated as a goal function of a tri-map and can be a powerful means of validating the separability of predefined feature distributions. Further, we propose a split-and-validate strategy for decomposing the complex problem into a series of tractable subproblems, and suboptimal tri-map optimization is gradually achieved by making decisions between cluster-level operations. The splitting is determined by a novel combination of Bregman hierarchical clustering and an information theoretic method for realizing non-parametric clustering. We have evaluated our method against the Oxford Flower 17 and Caltech-UCSD Bird 200 benchmarks and show the superiority of tri-map self-validation in unsupervised foreground segmentation tasks.