Active Contours driven by Local Pre-Fitting Energy for Fast Image Segmentation


Local fitting-based active contour models can segment images with intensity inhomogeneity effectively, but they are time-consuming and often fall into local minima. In this paper, we present an active contour model using local pre-fitting energy for fast image segmentation. The core idea of local pre-fitting energy is to define two pre-fitting functions by computing average image intensities locally before the evolution of curve. Experiments have shown that the proposed model is robust to initialization, which allows the initial level set function to be a small constant function. And it costs less segmentation time compared to other local fitting-based models. In addition, the proposed local pre-fitting method can be applied to other local fitting-based models to improve the robustness of initial contours and reduce the computational costs.