Image segmentation based on anisotropic diffusion and graph cuts optimisation

An image segmentation approach, which is based on heat diffusion and graph cuts optimisation, is proposed. The prior segmentation result is obtained by temperature maximisation on the heat diffusion system. In the random walk-based label-assigning process, due to lack of spatial dependencies of neighbouring pixels, the segmentation may deteriorate notably when pixels from disconnected regions of an image show similar features. To overcome this problem, a multilayer graph-based model is presented and image segmentation is considered as an energy minimisation problem. The parameters in the model are learned from the results of temperature maximisation on the heat diffusion system. It is shown that the presented variational model can be discretely optimised by the graph cuts method efficiently. Therefore, the spatial dependences of the neighbouring pixels can be integrated to obtain better segmentation results. A number of comparison experiments demonstrate the superiority of the proposed method.