Deep Learning Shape Priors for Object Segmentation

Fei Chen, Huimin Yu, Roland Hu, Xunxun Zeng; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 1870-1877

In this paper we introduce a new shape-driven approach for object segmentation. Given a training set of shapes, we first use deep Boltzmann machine to learn the hierarchical architecture of shape priors. This learned hierarchical architecture is then used to model shape variations of global and local structures in an energetic form. Finally, it is applied to data-driven variational methods to perform object extraction of corrupted data based on shape probabilistic representation. Experiments demonstrate that our model can be applied to dataset of arbitrary prior shapes, and can cope with image noise and clutter, as well as partial occlusions.