A novel region-based active contour model via local patch similarity measure for image segmentation

It is always difficult to accurately segment images with intensity inhomogeneity because most of the representative local-based models only take into account rough local information and do not consider the spatial relationship between the central pixel and its neighborhood. In fact, the pixels on an image are closely correlated to their local neighborhood. Therefore, the spatial relationship of neighboring pixels is a crucial feature that can play a vital role in image segmentation. In this paper, we propose a novel region-based active contour model via local patch similarity measure for image segmentation. In the model, we make full use of the spatial constraints on local region-based models for controlling the amplitude of spatial neighborhood to the center pixel in the image domain. Specifically, we first construct a local patch similarity measure as the spatial constraint, which balances the noise suppression and the image details reservation. Second, we construct the novel model by integrating the patch similarity measure into a region-based active contour model. Finally, we add a regularization information term to the objective function to ensure the smoothness and stability of the curve evolution. Experimental results show that the model is better than other classical local region-based models.