具有仿射不变性的视网膜图像配准方法  

Retinal Image Registration Method with Affine Invariance

作　　者：邹北骥[1,3] 戴玉兰 朱承璋 劳承鹏[1,3] 刘宁 Zou Beiji;Dai Yulan;Zhu Chengzhang;Lao Chengpeng;and Liu Ning(School of Information Science and Engineering,Central South University,Changsha 410083;School of Literature and Journalism,Central South University,Changsha 410083;Mobile Health Ministry of Education-China Mobile Joint Laboratory,Changsha 410083)

机构地区：[1]中南大学信息科学与工程学院,长沙410083 [2]中南大学文学与新闻传播学院,长沙410083 [3]移动医疗教育部-中国移动联合实验室,长沙410083

出　　处：《计算机辅助设计与图形学学报》2019年第6期943-950,共8页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61573380,61702559);湖南省科技计划项目(2017WK2074);湖南省自然科学基金青年项目(2018JJ3686);中南大学创新创业师生共创项目(2017gczd016)

摘　　要：为解决眼底照相机视角发生变化的视网膜图像的配准问题,提出一种具有仿射不变性的局部特征配准方法.首先通过寻找连通的血管交点对应的最小包围矩形得到仿射不变的各向异性图像结构;然后通过旋转、采样和压缩操作将各向异性的图像结构变为含不同角度因素的各向同性的图像结构;最后使用尺度不变特征变换算法在各向同性的图像结构上提取特征点,并对特征点坐标进行匹配.在包含83组视网膜图像的私有样本集中的实验结果表明,该方法的均方根误差为 1.247±0.251 像素,能很好地解决视角和尺度变化问题.In order to solve the registration problem of retinal images with changes in the angle of view of the fundus camera, a local feature registration method with affine invariance is proposed. First, an affine-invariant anisotropic image structure is obtained by computing the minimal boundary rectangle of the connected domain corresponding to the vascular intersection point. Then, the anisotropic image structure is transformed into an isotropic image structure with different angular factors by rotating, sampling, and compression. Finally, using the feature invariant feature transform algorithm to extract feature points on the isotropic image structure, and the feature point coordinates are matched. The experimental results in a private sample set containing 83 groups of retinal images show that the root mean square error of the method is 1.247±0.251 pixels, which can solve the problem of perspective and scale change well.

关 键 词：图像配准 仿射不变 局部特征 各向异性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]