Research On Extraction Of Skeleton Outer Contour Based On Snake Model

As one research branch in the field of computer vision, processing medical image is an important application of computer graphics and digital image processing in the biomedical engineering. Extracting the object's contours from medical CT images is the foundation of diagnostic and science research. Active Contour Model is suitable to medical image segmentation and contour extracting due to its highly dynamic quality. The task of the thesis is to study the key points of applying Snake Model to extract the skeletal outer contour for medical images.To solve the problem of setting initialized contour in traditional model, the thesis proposes a new method based on central radiation algorithm which deals with it availably. Choose Gaussian filter to strengthen the searching scope of control points. The external force of control points is analysed in detail. Taking Greedy Algorithm as external force, connect the maximum in neighborhood to approach true edge. Aside, the control points achieve their dynamic change to uniform distribution in order to smooth the contour. Finally extract the contour of skeleton.In sequence of medical images the skeleton contour in adjacent frames changes much. According to prior knowledge and estimation of motion, the thesis introduces directional energy to ascertain moving direction and position of update point. It expands the research scope, divide contour, incorporates and insert key points; then apply improved three-dimensional energy formula to adjust the former contour, achieves three-dimensional reconstruction of skeleton, obtains intact tridimensional skeleton information.Finally, on the basis of the summarized work, the essay has put forward some useful suggestions in the later study work, which is in great favor of guiding the further study work.