基于核模糊C均值的眼底视网膜血管分割算法  

Method for retinal image vessel segmentation based on KFCM

作　　者：曾业战[1] 钱盛友[1] 刘畅[1] 

机构地区：[1]湖南师范大学物理与信息科学学院,长沙410081

出　　处：《计算机工程与应用》2011年第1期242-244,共3页Computer Engineering and Applications

基　　金：湖南省教育厅项目(No.06C517)

摘　　要：针对眼底视网膜图像对比度差、背景不一致的问题,提出了一种基于核模糊C均值的眼底视网膜血管分割算法。首先采用二维高斯匹配滤波预处理以增强血管,然后采用核模糊C均值算法对增强眼底图像进行分割,并根据血管与各类隶属度的关系自动合并聚类图像得到最终的血管图像。实验结果表明,该算法分割结果令人满意。Aiming at the weakness of poor contrast and the background area variance of retinal image,a method for retinal image vessel segmentation based on KFCM is presented.Firstly,the two-dimensional Gaussian matched filter is used to enhance the retinal image.Then based on kernel fuzzy C-means the enhanced retina image is segmented,according to relations between retinal vein image and the different clustering degree of membership merge clustering images automatically.Finally,the vessel image is obtained.The simulation results show that the performance of this method is satisfied.

关 键 词：匹配滤波 图像分割 核模糊C均值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]