当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术2020年22期

基于多尺度Frangi 滤波器的视网膜血管分割
袁盼,陈以
(桂林电子科技大学 电子工程与自动化学院,广西 桂林 541004)

摘  要:针对眼底视网膜图像对比度低,受病变区域边界干扰,很难正确提取血管细节的问题提出了一种基于多尺度Frangi 滤波器的视网膜血管分割的方法。首先对图像预处理,其次在Frangi 滤波器的基础上进行多尺度操作,完成对图像细节的增强;最后运用遗传算法优化的Otsu 进行阈值分割,得到最终的结果图。利用所提方法在DRIVE 数据库进行实验,仿真结果表明上述方法对细小血管的提取表现出良好的效果,具备很强的实用价值。


关键词:图像处理;视网膜血管;遗传算法;阈值分割



中图分类号:TP317.4         文献标识码:A         文章编号:2096-4706(2020)22-0116-04


Retinal Vessel Segmentation Based on Multi-scale Frangi Filter

YUAN Pan,CHEN Yi

(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China)

Abstract:Aiming at the problem that the fundus retinal image has low contrast and is disturbed by the boundary of the diseased area,it is difficult to correctly extract the details of the blood vessel. A method of retinal blood vessel segmentation based on multi-scale Frangi filter is proposed. Firstly,the image is preprocessed,and then multi-scale operations are performed on the basis of the Frangi filter to complete the enhancement of image details;finally,Otsu optimized by genetic algorithm is used for threshold segmentation to get the final result graph. Using the proposed method to conduct experiments on the DRIVE database,the simulation results show that the above method has a good effect on the extraction of small blood vessels and has strong practical value.

Keywords:image processing;retinal vessel;genetic algorithm;threshold segmentation


基金项目:国家自然科学基金(61862016);广西自然科学基金(2017GXNSFAA198283)


参考文献:

[1] 郑婷月,唐晨,雷振坤. 基于全卷积神经网络的多尺度视网膜血管分割 [J]. 光学学报,2019,39(2):119-126.

[2] MIRI M S,MAHLOOIIFAR A. Retinal Image AnalysisUsing Curvelet Transform and Multistructure Elements Morphologyby Reconstruction [J].IEEE Transactions on Biomedical Engineering,2011,58(5):1183-1192.

[3] 孟琳,刘静,曹慧,等. 基于Frangi 滤波器和Otsu 视网膜血管分割 [J]. 激光与光电子学进展,2019,56(18):127-133.

[4] ZHU C Z,ZOU B J,ZHAO R C,et al. Retinal vesselsegmentation in colour fundus images using Extreme Learning Machine [J].Computerized Medical Imaging and Graphics,2017,55:68-77.

[5] DASH J,BHOL N. A method for blood vessel segmentation inretinal images usingmorphological reconstruction [C]//2016 InternationalConference on Computer,Electrical&Communication Engineering.Kolkata:IEEE,2016:1-5.

[6] AARTI,GUPTA N. Performance evaluation of retinal vesselsegmentation using a combination of filters [C]//2016 2nd InternationalConference on Next Generation Computing Technologies (NGCT).Dehradun:IEEE,2016:725-730.

[7] 丘赟立,蒋先刚,熊娟. 基于Hessian 算子的多尺度视网膜血管增强滤波方法 [J]. 计算机应用与软件,2014,31(9):201-205.

[8] 种劲松,周孝宽,王宏琦. 基于遗传算法的最佳熵阈值图像分割法 [J]. 北京航空航天大学学报,1999(6):747-750.

[9] 于洋,孔琳,虞闯. 自适应粒子群集优化二维OSTU 的图像阈值分割算法 [J]. 电子测量与仪器学报,2017,31(6):827-832.

[10] STAAL J,ABRAMOFF M D,NIEMEJIER M,et al.Ridge-based vessel segmentation in color images of the retina [J].IEEETransactions on Medical Imaging,2004,23(4):501-509.


作者简介:

袁盼(1995—),男,汉族,安徽广德人,硕士研究生,研究方向:机器学习、图像处理;

陈以(1963—),男,汉族,广西玉林人,教授,硕士研究生,研究方向:智能控制、计算机应用技术。