A Model Set Based Object Segmentation Method Using Level Set Approach

摘要

A novel approach for model set based object segmentation is described. The proposed method enables the using of a model set to guide the object segmentation. The object shape model selection and segmentation based on the selected model is formulated as an integrated process of constrained contour energy minimization. The solution derived from this formulation produces an integrated searching process consisting of two alternating procedures of contour evolution and contour model fitting. The process stops at a final contour together with a distance measure to the selected model contour for model selection. The resulting contour with the smallest distance is then selected as the final result. Model selection and segmentation results are finally reported.