An advanced variational level set evolution for image segmentation
Aijuan Ni, Gaofeng Wei, Feng Tian, Xiaoli Qin, Jian Yang, Qiuming Sun, Xinwu Xie · 2012
In this paper, we present an advanced variational formulation based on distance regularized level set evolution(DRLSE)that forces the level set function to be close to a signed distance function, and therefore not only completely eliminates the need of the costly re-initialization procedure, but also allows more efficient numerical scheme than DRLSE and traditional level set methods. Our provided potential function for the regularization term of the internal energy term is improved on the forward and backward diffusion. The advanced distance regularized level set evolution(ADRLSE) avoids the undesirable side effect and the distortedness of the zero level contour and provides more efficient numerical schemes and more smoothed contour. The proposed algorithm has been applied to both simulated and real images with promising results. In particular, it appears to perform more efficient numeration more smoothed contour.