改进的人工鱼群算法和Powell法结合的医学图像配准  

Registration of Multi-Resolution Medical Images Using a Modified Artificial Fish-Swarm Algorithm Combined with Powell's Method

作　　者：赵海峰[1] 姚丽莎[1] 罗斌[1] 

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,合肥230039

出　　处：《西安交通大学学报》2011年第4期46-52,共7页Journal of Xi'an Jiaotong University

基　　金：国家自然科学基金资助项目(60772122);安徽省教育厅自然科学研究项目(KJ2008A145)

摘　　要：针对目前基于互信息图像配准的局部极值问题,提出了一种改进的人工鱼群算法和Powell算法结合的多分辨率医学图像配准算法.该算法采用新的相似性测度方法即归一化模糊加权互信息和归一化局部能量加权匹配度,利用多分辨率策略采用HPV插值,并采用改进的人工鱼群算法结合Powell算法完成医学图像的配准.采用改进的人工鱼群算法在图像的最低分辨率上进行全局优化,以全局最优值为初始值,结合Powell算法完成图像配准.这不仅基本解决了互信息函数和Powell算法的局部极值问题,还减少了数据的处理量,加快了配准速度.实验结果表明,文中算法与其他经典的配准算法相比,提高了配准的精确度和性能.A registration algorithm of multi-resolution medical images is proposed by using a modified artificial fish-swarm algorithm combined with Powell＇s method to address the local maxima of mutual information-based image registration. Fuzzy weighted normalized mutual information and normalized partial energy-weighted matching are proposed as new similarity measures, multi-resolution strategy and HPV interpolation are used, and global optimization is performed with the proposed registration algorithm. Experimental results and comparisons with some existing registration methods in multi-mode medical image registration show that the proposed algorithm improves registration accuracy and performance.

关 键 词：图像配准 改进的人工鱼群算法 Powell法 多分辨率 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]