Introducing Curvature into Globally Optimal Image Segmentation: Minimum Ratio Cycles on Product Graphs

While the majority of competitive image segmentation methods are based on energy minimization, only few allow to efficiently determine globally optimal solutions. A graphtheoretic algorithm for finding globally optimal segmentations is given by the Minimum Ratio Cycles, first applied to segmentation in [8]. In this paper we show that the class of image segmentation problems solvable by Minimum Ratio Cycles is significantly larger than previously considered. In

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Thomas Schoenemann, Daniel Cremers
• Keywords: Competitive Image Segmentation, Computer Vision, ICCV 2007, Image Segmentation Problems, Minimum Ratio Cycles