Multi-region level set image segmentation based on image cartoon-texture decomposition model

This paper presents a multi-region level set image segmentation method based on image cartoon - texture decomposition model. The image feature is extracted by using the image decomposition method. We represent the regions by the level set functions with constraint. The coupled Partial Differential Equations (PDE) related to the minimization of the functional are considered through a dynamical scheme. A modified region competition factor is introduced to guarantee no vacuum and non-overlapping between the neighbor regions, it also speed up the cure evolution functions, the final segmentation can be achieved after several iterations. Several experiments are conducted on both synthetic images and natural images, the results illustrate that the proposed multi-region segmentation method is fast and less sensitive to the initializations.