Deep Learning Shape Priors for Object Segmentation

In this paper, a nonparametric statistical shape model based on shape probabilistic representation is proposed for object segmentation. Given a set of training shapes, Cremers et al.'s probabilistic method is adopted to represent the shape, and then ...

Segmentation involves separating an object from the background in a given image. The use of image information alone often leads to poor segmentation results due to the presence of noise, clutter or occlusion. The introduction of shape priors in the ...

In this paper a new method using selective shape priors in a level set framework for image segmentation under occlusion is presented. To solve occluded boundaries, prior knowledge of shape of objects is introduced using the Nitzberg-Mumford-Shiota ...