基于算术调和均值距离测度的弹性图像配准  

Arithmetic harmonic mean divergence measure for elastic image registration

作　　者：杨金宝[1] 刘常春[2] 胡顺波[3] 

机构地区：[1]青岛大学信息工程学院,山东青岛266071 [2]山东大学控制科学与工程学院,济南250061 [3]临沂师范学院物理系,山东临沂276005

出　　处：《吉林大学学报（工学版）》2009年第5期1390-1394,共5页Journal of Jilin University:Engineering and Technology Edition

基　　金：'863'国家高技术研究发展计划项目(2006AA02Z4D9);山东省自然科学基金项目(Z2006C05)

摘　　要：针对图像配准中的特征提取问题,提出了一种基于自动选取标记点的弹性图像配准方法。首先,提出了新的相似性测度,算术-调和均值距离测度AHM,图像通过最大化AHM全局配准,然后将图像划分成均匀子块,采用AHM测度刚性配准各对应子块,选取对应子块的中心作为标记点对,最后,用三次均匀B样条实现图像的弹性配准。实验结果表明,AHM是有效的,其配准速度是互信息的2倍。To solve the problem of feature extraction in image registration, an automatic method to extract landmark points for elastic medical image registration is proposed. First, a new similarity measure, named as arithmetic harmonic mean divergence measure （AHM）, is induced. The reference image and floating image are rigidly registered by AHM measure. Then, the two images are divided into uniform blocks. The landmarks in object are extracted by regional rigid registration by maximizing AHM measure between the corresponding subimages. According to corresponding landmarks, the global elastic registration is achieved by bicubic B-spline functions. Experiments on registration of brain Magnetic Resonance （MR） images and Computed Tomography （CT） images show that the proposed method is accurate and fast.

关 键 词：信息处理技术 弹性配准 算术-调和均值距离 互信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]