摘要
基于互信息的配准方法具有精度高、鲁棒性强的特点,成为近年图像配准研究的热点,但基于互信息的目标函数存在许多局部极值,为配准的优化过程带来了很大的困难。本文以互信息作为相似性测度,采用基于小波变换的多分辨率策略,将遗传算法和Powell法结合起来对三维CT、MR图像进行了配准。实验结果表明,这种方法能够有效地克服信息函数的局部极值,配准精度达到亚像素级。
This paper proposes an image registration method based on wavelet representation,in which the mutual information is used as the similarity measure and a hybrid algorithm based on the genetic algorithm and Powell's method is used as the search technique, The experimental results show that this registration method could efficiently restrain the local maxima of mutual information function and the subvoxel accuracy can be achieved.
出处
《光电子.激光》
EI
CAS
CSCD
北大核心
2006年第6期755-758,共4页
Journal of Optoelectronics·Laser
基金
湖南大学校基金资助(2004018)
关键词
图像配准
互信息
遗传算法
Powell法
image registration
mutual information
genetic algorithm
Powell's method