Globally Optimal Image Partitioning by Multicuts

Abstract. We introduce an approach to both image labeling and unsupervised image partitioning as different instances of the multicut problem, together with an algorithm returning globally optimal solutions. For image labeling, the approach provides a valid alternative. For unsupervised image partitioning, the approach outperforms state-of-the-art labeling methods with respect to both optimality and runtime, and additionally returns competitive performance measures for the Berkeley Segmentation Dataset as reported in the literature. Key words: image segmentation, partitioning, labeling, multicuts, multiway cuts, multicut polytope, cutting planes, integer programming

• Type: Journal
• Year: 2011
• Where: EMMCVPR
• Authors: Jörg H. Kappes, Markus Speth, Björn Andres, Gerhard Reinelt, Christoph Schnörr
• Keywords: Computer Vision, EMMCVPR 2011, Image Segmentation, Integer Programming, Performance Measures