Title :
Deep Learning Shape Priors for Object Segmentation
Author :
Fei Chen ; Huimin Yu ; Hu, Rose ; Xunxun Zeng
Author_Institution :
Dept. of Inf. Sci. & Electron. Eng., Zhejiang Univ., Hangzhou, China
Abstract :
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.
Keywords :
Boltzmann machines; computer vision; feature extraction; image representation; image segmentation; learning (artificial intelligence); probability; computer vision; corrupted data object extraction; data-driven variational methods; deep Boltzmann machine; deep learning shape priors; hierarchical shape prior architecture learning; image clutter; image noise; object segmentation; shape probabilistic representation; shape variation model; Computational modeling; Image segmentation; Mathematical model; Object segmentation; Probabilistic logic; Shape; Training; Boltzmann machine; Deep learning; segmentation; shape priors; variational methods;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPR.2013.244