Hybrid Active Contours Driven by Improved Laplace Adaptive Energy in Multiphase Level Set Framework

Abstract

This paper presents a novel multiphase level set framework and its corresponding algorithms for image segmentation. The region fitting energies are described with the combination of the global and local distributions. An improved image Laplace term enhances the ability to locate the weak boundary. In order to better deal with the inhomogeneity, the adaptive segmentation energy is proposed to replace the fixed threshold and local Gaussian means and variances are added to get better precision of segmentation results. Experiment shows the proposed model is effective with application to MR images with intensity inhomogeneity.