基于水平集曲线演化的目标轮廓提取

基于水平集的曲线演化与活动轮廓模型相结合，产生了几何活动轮廓模型，由于其良好的特性，在图像分割领域已经有了广泛的应用。本文对于一种耦合的活动轮廓模型，应用变分法求解出其对应的水平集曲线演化的偏微分方程，并给出了解的存在惟一性证明，然后将它应用到图像分割和目标轮廓提取中，取得了良好的效果。

Object Contour Extraction Based on Curve Evolution via Level Set

On the basis of level set methods, curve evolution and active contour models, geometric active contour models come into being. It has been widely used in image segmentation for its good characteristics. Toward a given coupled active contour models, this paper seeks the partial differential equations corresponding to the level set evolution according to variational principle and gives the proof of the existence, uniqueness of the solution. At last, it has been applied to image segmentation and boundary extraction. The results show that the new approach is more accurate and robust and can obtain very good effect.