Growing snakes: active contours for complex topologies

Snakes are active contours that minimize an energy function. In this paper we introduce a new kind of snakes, called growing snakes. These snakes are modeled as a set of particles connected by thin rods. Unlike the traditional snakes, growing snakes are automatically initialized. They start at the position where the gradient magnitude of an image is largest, and start to grow looking for zones of high gradient magnitude; simultaneously the associated energy function is minimized. Growing snakes can find contours with complex topology, describing holes, occlusions, separate objects and bifurcations. In a post-process the T-junctions are refined looking for the configuration with minimal energy. We also describe a technique that permits one to regularize the field of external forces that act on the Growing Snakes, which allow them to have good performance, even in the case of images with high levels of noise. Finally, we present results in synthetic and real images.