摘要
目的目前医生一般通过检眼镜等设备查看眼病患者眼底结构特征诊断疾病,工序烦琐、存在误差并受主观因素的影响,诊断效率低。因此有必要开发一款眼底数码图像处理系统配合医生诊断。方法对原始图像进行增强对比度和空域滤波的预处理操作、二值化处理、形态学处理及边缘提取和骨架提取,进而得到目标特征区域。结果本文初步研究眼底数码图像视杯、视盘和血管轮廓特征的自动提取关键技术,通过MATLAB仿真软件对特征提取关键技术进行总结和验证,归纳出提取不同眼底特征时的应对策略。结论利用数字图像处理技术可以自动识别眼底数码图像中的不同特征区域,建立眼底数码图像处理系统用于辅助医生诊断是可行的。
Objective Fundus abnormalities caused by diseases can be shown in the main components of the fundus, diagnosed by clinical ophthalmologists using the equipment like ophthalmoscope, witch influenced by complex method, subjective fault and low efficiency. Hence, it is necessary to develop a computer-aided fundus image processing system as a tool to assist in the diagnosis diseases. Methods Some algorithms are proposed including the pre-processing such as contrast enhancement and spatial filtering, binaryzation, morphology, boundary extraction and skeleton extraction. Results This paper preliminary summarized the key technologies and the strategy of fundus digital image processing, an automated detection of optic cup, optic disc and blood vessel, by the simulating experiment in MATLAB. Conclusions Fully automated computer algorithms are able to detect main components of fundus images. This paper presents encouraging results in computer-aided fundus image processing system.
出处
《北京生物医学工程》
2014年第1期7-12,共6页
Beijing Biomedical Engineering
基金
北京市优秀人才项目(2011D005015000008)资助
关键词
眼底数码图像
视杯
视盘
血管轮廓
自动检测
fundus
optic disc
optic cup
blood vessel
image processing
automated detection
