 |
    |
Convexity Shape Prior for Segmentation
Lena Gorelick1, Olga Veksler1, Yuri Boykov1, and Claudia Nieuwenhuis2
1University of Western Ontario, Canada
2UC Berkeley, USA
Abstract. Convexity is known as an important cue in human vision. We propose shape convexity as a new high-order regularization constraint for binary image segmentation. In the context of discrete optimization, object convexity is represented as a sum of 3-clique potentials penalizing any 1-0-1 configuration on all straight lines. We show that these non-submodular interactions can be efficiently optimized using a trust region approach. While the quadratic number of all 3-cliques is prohibitively high, we designed a dynamic programming technique for evaluating and approximating these cliques in linear time. Our experiments demonstrate general usefulness of the proposed convexity constraint on synthetic and real image segmentation examples. Unlike standard second-order length regularization, our convexity prior is scale invariant, does not have shrinking bias, and is virtually parameter-free.
Keywords: segmentation, convexity shape prior, high-order functionals, trust region, graph cuts
LNCS 8693, p. 675 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014