基于过渡区提取的视网膜血管分割方法

被引：19

作者：

姚畅

陈后金

李居朋

机构：

[1] 北京交通大学电子信息工程学院

来源：

电子学报 | 2008年 / 05期

关键词：

血管分割; 过渡区; 最佳熵; 分布式遗传算法; 最大类间方差;

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

针对现有视网膜血管分割方法对于小血管和低对比度血管分割效果差的问题,提出了一种基于过渡区提取的视网膜血管分割方法.该方法首先采用二维高斯匹配滤波预处理以增强血管,然后采用基于最佳熵的方法提取主血管、采用基于分布式遗传算法和Otsu相结合的方法提取过渡区,最后利用区域连通性分析所提取的主血管和过渡区,分割出最终的血管.通过在Hoover眼底图像库中的实验,结果表明该方法在小血管的提取、连通性和有效性方面均优于Hoover算法,另外由于迁移策略的分布式遗传算法的引入,使得算法效率也明显提高.

引用

页码：974 / 978

页数：5

共 8 条

[1]

Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm. Sun Y. IEEE Transactions on Medical Imaging . 1989

[2]

Detection of bloodvessels in retinal images using two-dimensional matched filters. Chaudhuri S,,Chatterjee S,Katz N,et al. IEEE Transactions on Medical Imaging . 1989

[3]

A method for segmentation of retinalimage vessels. Huang S Y,Zhang E H. Proceedings of the6th World Congress onIntelligent Control and Automation . 2006

[4]

A threshold selection method from gray-level his-tograms. Otsu N. IEEE Transactions on Systems,Man,and Cyber-netics . 1979

[5]

A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering. Tolias YA,Panas SM. IEEE Transactions on Medical Imaging . 1998

[6]

Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images. Jiang XY,Mojon D. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2003

[7]

Volumetric Segmentation of Brain Images Using Parallel Genetic Algorithm. F. Yong,T.Z. Jiang,and D.J. Evans. IEEE Transactions on Medical Imaging . 2002

[8]

Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. Hoover A,Kouznetsova V,Goldbaum M. IEEE Transactions on Medical Imaging . 2000

← 1 →