New image segmentation model based on the level set method

A novel variational model based on the level set method is proposed. In the model, we introduce a nonconvex regularizer which performs better than the convex ones on protecting edges. On the other hand, the nonconvex regularizer is designed to provide a force which can help the evolution of the level set function. The Nesterov algorithm is introduced to implement the model. Experiments demonstrate the advantages of the proposed method over the Chan-Vese model in terms of both efficiency and accuracy.