Active contours driven by local and global intensity fitting energies based on local entropy

Abstract This paper proposes an improved region-based active contour model. A novel region-scalable fitting energy term which based on the local entropy deriving from a grey level distribution of image is defined. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. The combination of these two terms is then incorporated into a variational level set formulation with two extra regularization terms that are necessary for accurate computation in the corresponding level set method. The resulting evolution of the level set function is the gradient flow that minimizes the overall energy functional. The proposed method has been tested on synthetic and real images, and the experiment results show that our method is efficient and robust for segmenting images with noisy and intensity inhomogeneity.