Automatic Shape Constraint Selection Based Object Segmentation

In this paper, an object segmentation algorithm based on automatic shape constraint selection is proposed. Different from the traditional shape prior based object segmentation methods which only provide loose shape constraints, our proposed object segmentation gives more accurate shape constraint by selecting the most appropriate shape among the standard shape set. Furthermore, to overcome the inevitable differences between the true borders and the standard shapes, the Coherent Point Drift (CPD) is adopted to project the standard shapes to the local ones. A quantitative evaluating mechanism is introduced to pick out the most suitable shape prior. The proposed algorithm mainly consists of four steps: 1) the initial GrabCut segmentation; 2) standard shape projection by CPD registration; 3) rank the standard shapes according to the evaluation scores; 4) refine GrabCut segmentation with the chosen shape constraint. The comparison experiments with the related algorithms on Weizmann_horse dataset have demonstrated the good performance of the proposed algorithm.