Adaptive Level Set Model For Image Segmentation Based On Tensor Diffusion

According to the tensor diffusion theory, this paper proposes a novel active contour model for image segmentation in the level set formulation. Firstly, we define an external energy term using the trace-based tensor diffusion equation, which can locate the evolution curve to the neighborhood of one target boundaries adaptively. So it will enhance the robustness of the model to the initialization of contour. Secondly, an internal energy term is established based on the eigenvalues' information of image structure tensor, which can push the evolution curve to the target boundaries, so as to further improve image segmentation accuracy. Experimental results on both synthetic and real images show desirable performances of our method.