A framework for multiple snakes and its applications

摘要

We present a framework for segmentation of multiple objects whose shapes are similar but image qualities are different. Our framework is based on the snake or active contour method, in which a new kind of energy called “group energy” is introduced. The group energy is used to handle the sharing of properties across multiple objects and also to allow contours of objects with good image qualities to be used as reference contours for remaining objects during optimization. In this framework, we also deal with rotations among similar objects by applying group energy after removing the rotation offset. Comprehensive testing has been performed on synthetic and real images, demonstrating that our framework has significantly better performance of segmentation compared to the original (individual) snake.