水平集方法中速度停止项函数的改进

A Modified Speed Stop Function of Level Set Method

对速度停止项函数的研究发现,现今的速度停止项采用的单一全局阈值法很难使经典水平集算法得到较准确的分割效果。为此,提出了一种新的速度停止项函数,该函数通过引入变阈值较好的区分了图像的边缘区与同质区,以使采用该速度停止项函数的水平集方程实现在同质区加速演化,在边缘区停止演化的目的。实验结果表明,采用速度停止项函数能够使水平集方法获取更好的分割结果。

Studying on speed stop function was found that using globe threshold based speed stop function would get poor segmentation of the classical level set.So a new speed stop function of level set was proposed.In the new speed stop function,an adaptive threshold was used to distinguish the edge and homogeneous area of the image,which can make the level set evolving faster in homogeneous area and stop in edge.Finally,the experimental results showed that using the developed speed stop function based level set is verified well than the traditional one.