Coupled Region-Edge Shape Priors for Simultaneous Localization and Figure-ground Segmentation Cheng Chen and Guoliang Fan School of Electrical and Computer Engineering Oklahoma State University, Stillwater, OK 74078, USA Tel/fax: +1 (405) 744-1547/+1 (405) 744-9198 Email: guoliang.fan@okstate.edu Abstract We propose a new algorithm for simultaneous localization and figure-ground segmentation where coupled region-edge shape priors are involved with two different but complementary roles. We resort to a segmentation-based hypothesis- and-test paradigm to solve the problem, where the region prior is used to form a segmentation and the edge prior is used to evaluate the validity of the formed segmentation. Our fundamental assumption is that the opti- mal shape-constrained segmentation that maximizes the agreement with the edge prior occurs at the correctly hypothesized location. Essentially, the pro- posed algorithm addresses a mid-level vision issue that aims at producing a map image for part detection can be further used for high-level vision tasks. Our experiments demonstrated that this algorithm offers promising results in terms of both localization and segmentation. Key words: figure-ground segmentation, shape priors, segmentation, localization, watersheds, online learning, kernel-based color modeling 1. Introduction Segmentation is an important and long-standing research topic in the fields of image analysis and computer vision, and it can be done at differ- ent levels. At low-level vision, it is called image segmentation that is to group pixels into regions of homogeneous properties based on various low- level region-based cues (e.g., intensity, color, or texture) and/or edge-based cues (e.g., boundaries or local gradients). Combining both region-based and edge-based cues has led to significant successes for image segmentation due Preprint submitted to Pattern Recognition January 27, 2010