摘要
提出了一种结合全局配准和局部配准技术的眼底图像二级配准算法,该算法采用4个相连的分叉点组成的局部血管结构来代替单独的分叉点作为配准特征,通过减少配对点集,提高了配准效率.同时针对非线性形变造成的局部配准偏移较大的问题,在全局配准基础上进一步采用局部配准技术,提升了配准的准确度.实验结果表明,该算法以很高的配准效率和准确度有效实现了眼底图像的配准.
A two-stage registration algorithm combining global registration and local registration technology is proposed.In this algorithm,bifurcation structures with 4 connected bifurcation points rather than single bifurcation points are used as the registration features.By reducing pairing points,the efficient of registration is improved.Moreover due to non-linear deformation,there are some registration errors appear in some local region.To solve this problem,a local registration technology is introduced according to the global registration results,which improve registration precision.Experiment results show that the algorithm effectively achieve fundus image registration with higher efficient and precision.
出处
《光子学报》
EI
CAS
CSCD
北大核心
2012年第10期1236-1241,共6页
Acta Photonica Sinica
基金
国家自然科学基金(No.60835004)
湖南省科技厅项目(No.2012FJ3113)
湖南省教育厅科研项目(No.10B109)资助
关键词
局部特征
分叉点
分叉结构
特征提取
配准
Local feature
Bifurcation point
Bifurcation structure
Feature extraction
Registration