《计算机应用研究》|Application Research of Computers

改进的形态学与Otsu相结合的视网膜血管分割

New approach to segment retinal vessel using morphology and Otsu

免费全文下载 (已被下载 次)  
获取PDF全文
作者 汪维华,张景中,吴文渊
机构 1.中国科学院重庆绿色智能技术研究院 自动推理与认知重庆市重点实验室,重庆 400714;2.中国科学院大学 计算机与控制学院,北京 100049;3.重庆文理学院 软件工程学院,重庆 402160
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)07-065-2228-04
DOI 10.19734/j.issn.1001-3695.2018.01.0122
摘要 针对视网膜图像采集过程中由于疾病引起的图像光照反射过强问题,提出了一种修正的形态学与Otsu相结合的无监督视网膜血管分割算法。首先运用形态学中的高低帽变换增强血管与背景的对比度;然后提出了一种修正方法,消除部分由视网膜疾病引起的光照问题;最后使用Otsu阈值方法分割血管。算法在DRIVE和STARE视网膜图像数据库中进行了测试,实验结果表明,DRIVE数据库中的分割精度为0.938 2,STARE数据库中的分割精度为0.946 0,算法的执行时间为1.6 s。算法能够精确地分割出视网膜血管,与传统的无监督视网膜血管分割算法相比,算法的分割精度高、抗干扰能力强。
关键词 视网膜血管; 大津法; 形态学; 图像分割; 图像增强
基金项目 国家自然科学基金资助项目(11501540,11471307)
中国科学院西部之光基金资助项目
重庆市教委科技项目(KJ1501120,KJ1401118)
本文URL http://www.arocmag.com/article/01-2019-07-065.html
英文标题 New approach to segment retinal vessel using morphology and Otsu
作者英文名 Wang Weihua, Zhang Jingzhong, Wu Wenyuan
机构英文名 1.Chongqing Key Laboratory of Automated Reasoning & Cognition,Chongqing Institute of Green & Intelligent Technology,Chinese Academy of Sciences,Chongqing 400714,China;2.School of Computer & Control Engineering,University of Chinese Academy of Sciences,Beijing 100049,China;3.School of Software Engineering,Chongqing University of Arts & Sciences,Chongqing 402160,China
英文摘要 To enhance the image with imbalanced local illumination caused by retinal diseases in the process of fundus image acquisition, this paper proposed a new unsupervised retinal vessel segmentation method with morphological and Otsu. First, it used the combine of the top-hat transformation and the bottom-hat transformation to enhance the contrast between the blood vessels and its background in a retinal image. Next, it presented a novel revised method to remove the problem, which was caused by the imbalanced local illumination in the enhanced retinal image. Finally, it applied the threshold calculated by Otsu method to extract the retinal vessels. This paper evaluated the algorithm with two publicly retinal image databases DRIVE and STARE. The experiment results indicate that the segmentation accuracy in DRIVE database achieves 0.938 2, the segmentation accuracy in the STARE database achieves 0.946 0. The run time of this new method is 1.6 s. The new algorithm can accurately extract the retinal vessels. Compared with the traditional retinal vessel segmentation algorithm, its segmentation accuracy and anti-perturbation ability improve.
英文关键词 retinal vessel; Otsu; morphology; image segmentation; image enhancement
参考文献 查看稿件参考文献
 
收稿日期 2018/1/31
修回日期 2018/3/22
页码 2228-2231
中图分类号 TP319
文献标志码 A