Explicit order model for region-based level set segmentation

Region-based level set methods have been widely used for image segmentation. Among them, the method based on local binary fitting (LBF) model is an efficient one. Unfortunately, LBF model is sensitive to initial contour. To overcome this disadvantage, we propose two explicit order models, i.e., the global order preserving and local order smoothness models. The global order preserving model ensures that the binary fitting values have the same order globally, while the local order smoothness model requires that these orders are smooth locally. With these two models, our segmentation results are not sensitive to initializations. Experimental results on synthetic and real images show desirable performances of our method, as compared with the state-of-the-art approaches.