首页 | 官方网站   微博 | 高级检索  
     

基于局部血管结构特征的眼底图像二级配准
引用本文:沈奔,张东波,彭英辉.基于局部血管结构特征的眼底图像二级配准[J].光子学报,2012,41(10):1236-1241.
作者姓名:沈奔  张东波  彭英辉
作者单位:1. 湘潭大学 信息工程学院,湖南湘潭,411105
2. 湘潭大学 信息工程学院,湖南湘潭411105;湘潭大学 智能计算与信息处理教育部重点实验室,湖南湘潭411105
基金项目:国家自然科学基金(No.60835004)、湖南省科技厅项目(No.2012FJ3113)和湖南省教育厅科研项目(No.10B109)资助
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.

关 键 词:局部特征  分叉点  分叉结构  特征提取  配准
收稿时间:2012/5/7

Two-stage Retinal Fundus Image Registration Based on Local Blood Structure Features
SHEN Ben , ZHANG Dong-bo , PENG Ying-hui.Two-stage Retinal Fundus Image Registration Based on Local Blood Structure Features[J].Acta Photonica Sinica,2012,41(10):1236-1241.
Authors:SHEN Ben  ZHANG Dong-bo  PENG Ying-hui
Affiliation:a(a.College of Information Engineering;b.Key Laboratory of Intelligent Computing & Information Processing(Ministry of Education),Xiangtan,Hunan 411105,China)
Abstract: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.
Keywords:Local feature  Bifurcation point  Bifurcation structure  Feature extraction  Registration
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号