Using the GGVF for automatic initialization and splitting snake model

This communication presents a simple approach to automatic initialization and splitting snake model for segmentation of Computed Tomography (CT) images. Image segmentation is carried out by means of snake algorithm and the dynamic programming (DP) optimization technique. With the generalized gradient vector flow (GGVF) field, a new strategy for contour points initialization and splitting is proposed in this communication. Contour initialization is carried out from GGVF magnitude thresholding. In the multi-object image segmentation, splitting of the contour to segment all the image objects is managed using the divergent points in the image. The proposed technique can attain a good solution without the need of operator intervention. Some experiences on synthetic and CT medical images show that the proposed algorithm gives good results.