Coupled region-edge shape priors for simultaneous localization and figure-ground segmentation

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 hypothesisand-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 optimal shape-constrained segmentation that maximizes the agreement with the edge prior occurs at the correctly hypothesized location. Essentially, the proposed 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 ...

• Type: Journal
• Year: 2010
• Where: PR
• Authors: Cheng Chen, Guoliang Fan
• Keywords: Optimal Shape-constrained Segmentation, PR 2010, Shape Priors, figure-ground Segmentation