Active contour models are very popular in image segmentation. Different features such as mean gray and variance are selected for\ndifferent purpose. But for image with intensity inhomogeneities, there are no features for segmentation using the active contour\nmodel. The images with intensity inhomogeneities often occurred in real world especially in medical images. To deal with the\ndifficulties raised in image segmentation with intensity inhomogeneities, a new active contour model with higher-order diffusion\nmethod is proposed.With the addition of gradient and Laplace information, the active contour model can converge to the edge of\nthe image even with the intensity inhomogeneities. Because of the introduction of Laplace information, the difference scheme\nbecomes more difficult. To enhance the efficiency of the segmentation, the fast Split Bregman algorithm is designed for the\nsegmentation implementation.The performance of our method is demonstrated through numerical experiments of some medical\nimage segmentations with intensity inhomogeneities.
Loading....