Fast Multiregion Image Segmentation Using Statistical Active Contours

Abstract-In the first place, here propose a novel statistical active contours method for using an arbitrary number of level set functions tosegment an image into regions of the corresponding amount. First, a new updating of level set functions for every region is derivedfrom the probabilistic models of image data. Second, a novel geometric prior that deduced from the level-set-based curve evolutionis introduced to obtain the probabilistic label. Therefore, updatingof the level set functions and estimation of the distribution parameter are run alternately in a fast manner. Finally, in order to furtherenhance the efficiency. To say nothing of, initialize the level set function by thestatistical approach to draw near object boundary. Although this may be true, experimentally evaluate our proposed approach on complicated real-worldimages and demonstrate its good performance in practice