快速CV双水平集算法的人脑MR图像分割  

Fast Chan-Vese Multiphase Level Set Algorithm on Human Brain MR Image Segmentation

作　　者：詹天明[1] 张建伟[1] 陈允杰[1] 王宇[1] 吴玲玲[1] 

机构地区：[1]南京信息工程大学数理学院,南京210044

出　　处：《计算机工程》2009年第14期181-183,共3页Computer Engineering

基　　金：江苏省教育厅"青蓝工程"基金资助项目(2006)

摘　　要：针对CV模型的多水平集算法需要较高的数值稳定性以及曲线演化速度慢的缺点,根据人脑MR图像的特征,提出一种快速CV双水平集算法,统计被2条曲线划分成4类的直方图,构造符号矩阵,依次将直方图上的点放入其他类中,根据能量的变化更改该点对应点的符号,得到粗分割结果,并对粗分割结果进行优化。对MR图像进行的分割实验表明,其分割效果更好,速度有大幅度的提高。Multiphase level set method of Chan-Vese（CV） model is not suitable for real-time application for having numerical stability constraints and its low efficiency. Aiming at this disability and based on the specialty of human brain, a fast method to solve is developed. This approach computes the histograms of four areas which can be used to distinguish the area cut by two curves, and constructs signed tables. The points of the histogram are changed to other clusters and the sign of the points are checked according to the change of the energy. And the improved mean of small neighborhood method is used to optimize the results and get the final edges. Experimental results show that the new model can get the better results in an efficient way.

关 键 词：CV模型 直方图 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]