基于小波变换和混合遗传算法的医学图像配准.pdf

31 4 Vol. 31 No.4 2010 7 Journal of Applied Optics Jul. 2010 : 1002-2082(2010) 04-0589-04 1 2 1 1 1 梁君婷, 董　友 , 王明泉, 赵月萍, 冯晓夏 ( 1. , 030051; 2. , 036000) 摘　要: 为了解决灰度图像配准中由于目 函数容易陷入局部极值而造成的误匹配问题, 使参数 随图像的NMI 计算和多分辨率级数进行自适应调整, 采用基于小波变换多分辨率策略, 形成多尺 度匹配模型, 并将粒子群算法( PSO) 作为添加算子, 提出了以图像归一化互信息 ( NMI) 作为 相似性测度的混合遗传算法, 对CT 与MRI 图像进行了配准。实验结果表明, 该方法能够解决遗 传算法早熟收敛问题, 有效地克服信息函数的局部极值, 实现图像的自动配准, 具有匹配精确、鲁 棒性好及效率高等优点。 关键词: 混合遗传算法; 图像配准; 小波变换; Powell 算法; 互信息 : TN911.73; TP391: A Medical image registration based on wavel et transf orm and hybrid genetic algorithm 1 2 1 1 1 - , , - , - , - IANG Jun ting DONG You WAN G Ming quan ZHAO Yue ping FENG Xiao xia ( 1. T he Ministry of Education Key ab for Instrumentation Science and Dynamic T est , North University of China, Taiyuan 030051, China; 2. No. 1 Middle School of Shuocheng District Shuozhou, , 036000, China) Abstract: To address the disadvantages of image registration, a new method for image registration is proposed, which combines hybrid genetic algorithm with wavelet multi-resolution analysis strategy In this method mutual information is used as the similarity measure and a. , hybrid genetic algorithm is used as the search technique, and the parameters of genetic algorithm are adapted along with the computation of mutual information and the multi-resolution of the images T he experimental results show that this registration method could efficiently restrain. the local maxima of mutual information function and the subv