Multicue Graph Mincut for Image Segmentation

We propose a general framework to encode various grouping cues for natural image segmentation. We extend the classical Gibbs energy of an MRF to three terms: likelihood energy, coherence energy and separating energy. We encode generative cues in the likelihood and coherence energy to ensure the goodness and feasibility of segmentation, and embed discriminative cues in the separating energy to encourage assigning two pixels with strong separability with different labels. We use a self-validated process to iteratively minimize the global Gibbs energy. Our approach is able to automatically determine the number of segments, and produce a natural hierarchy of coarse-to-fine segmentation. Experiments show that our approach works well for various segmentation problems, and outperforms existing methods in terms of robustness to noise and preservation of soft edges.