Research On Active Contour Model

Active Contour Model, or Snake model, which was first introduced by Kass, has been used extensively in many applications of computer vision and image processing, such as edge detection, image segmentation and motion tracking, particularly to extract object boundaries. With the introduction of high level information, Snake model has more satisfactory effects than what gained by the traditional method when dealing with disconnected edges in the image.The interior limitation of the traditional Snake model has caused the severe disadvantage, which is the disability to exract boundary concavities. A combined Snake is presented here to solve the poor convergence to boundary concavities which exists in the traditional Snake model. The combined Snake model leads the action of the active contour curve with the instruction of both intensity feature of the image and the figure feature of the object, so as to push the energy-minimizing curve to the concave parts of the interested objects.Quite different from the traditional Snake model, the combined model is made up of two modules: the global model and the local one. At first, we detect the coarse boundary in the early time of the algorithm by the global model; then, further detect the concave parts of the boundary by the local model based on the detection of the concave points by the use of SUSAN operator. In the end, a whole contour is gained by the fusion of both effects extracted by the global model and the local one.