A New Image Segmentation Method for Removing Background of Object Movies by Learning Shape Priors
Cheng-Hung Ko, Yu-Pao Tsai, Zen-Chung Shih, Yi-Ping Hung · 2006
This paper proposes a new object movie (OM) segmentation method that incorporates shape priors into the segmentation algorithm. The shape prior introduced into every image of the OM is learned from the 3D model reconstructed by the volumetric graph cuts. Here, the constraint derived from the discrete medial axis is used to improve the reconstruction algorithm. Our segmentation method requires only a small amount of user intervention, which is to select a subset of acceptable segmentations of the OM after the initial segmentation process. Compared to other techniques, our method provides not only the better segmentation result but also the better 3D reconstruction result