A hybrid active contour model with structured feature for image segmentation

We propose a structural feature region-based active contour model based on the level set method for image segmentation. Firstly, an anisotropic data fitting term is proposed to adaptively detect the intensity both in terms of local direction and global region. Secondly, coupling with the duality theory and a structured gradient vector flow (SGVF) method, a new regularization term of the level set function is formulated to penalize the length of active contour. By this new regularization term, the structured information of images is utilized to improve the ability of preserving the elongated structures. The energy function of the proposed model is minimized by an efficient dual algorithm, avoiding the instability and the non-differentiability of traditional numerical solutions. We compare the proposed method to classical region-based active contour models and highlight its advantages through experiments on synthetic and medical images.