Abstract
Image segmentation and figure/ground organization are fun- damental steps in visual perception. This paper introduces an algorithm that couples these tasks together in a single grouping framework driven by low-level image cues. By encoding both affinity and ordering prefer- ences in a common representation and solving an Angular Embedding problem, we allow segmentation cues to influence figure/ground assign- ment and figure/ground cues to influence segmentation. Results are com- parable to state-of-the-art automatic image segmentation systems, while additionally providing a global figure/ground ordering on regions.