A restarted iterative homotopy analysis method for three-dimensional image segmentation

Total variational segmentation models provide effective tools for identifying all features and their boundaries in two and three dimensional images and have been proven to be useful and successful. Speeding up a simulation is one of the remaining challenges. In this paper we propose a restarted homotopy analysis method to improve the computational efficiency in three-dimensional image segmentation. The algorithm replaces the nonlinear variational problem by a sequence of linear approximations by working with linear equations instead of nonlinear ones which lead to efficient energy minimization while maintaining the segmentation quality. Experimental results will show that the computational efficiency is significantly improved.