Convex Shape Priors for Level Set Representation
This work provides a principled way to incorporate convex shape priors into level set-based optimization, which is useful for image segmentation and other shape optimization problems.
The authors propose a necessary and sufficient condition on level set functions to enforce convexity of represented shapes, and demonstrate its application to image segmentation with landmark constraints. Numerical experiments validate the efficiency of the proposed models and algorithms.
For many applications, we need to use techniques to represent convex shapes and objects. In this work, we use level set method to represent shapes and find a necessary and sufficient condition on the level set function to guarantee the convexity of the represented shapes. We take image segmentation as an example to apply our technique. Numerical algorithm is developed to solve the variational model. In order to improve the performance of segmentation for complex images, we also incorporate landmarks into the model. One option is to specify points that the object boundary must contain. Another option is to specify points that the foreground (the object) and the background must contain. Numerical experiments on different images validate the efficiency of the proposed models and algorithms. We want to emphasize that the proposed technique could be used for general shape optimization with convex shape prior. For other applications, the numerical algorithms need to be extended and modified.