Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (18): 88-90.

• 网络、通信、安全 • Previous Articles     Next Articles

Method of retinal vessel segmentation based on Gabor wavelet

WANG Runmin1,YAO Chang2,LIU Jianxun3   

  1. 1.College of Information and Electrical Engineering,Hunan University of Science and Technology,Xiangtan,Hunan 411201,China
    2.School of Electronics and Information Engineering,Beijing Jiaotong University,Beijing 100044,China
    3.Knowledge Grid Laboratory,Hunan University of Science and Technology,Xiangtan,Hunan 411201,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-06-21 Published:2011-06-21

基于Gabor小波的视网膜血管自动提取研究

王润民1,姚 畅2,刘建勋3   

  1. 1.湖南科技大学 信息与电气工程学院,湖南 湘潭 411201
    2.北京交通大学 电子信息工程学院,北京 100044
    3.湖南科技大学 知识网格实验室,湖南 湘潭 411201

Abstract: In terms of the special gray distribution and region structure in retinal image,a novel blood vessel segmentation method based on Gabor wavelet is proposed.The Gabor wavelet is taken to enhance vessels,then the algorithm based on improved adaptive binarization is employed for the retinal image’s binarization processing,and the mathematical morphology is applied to extract the vessels region by analysis of region connectivity.The experiments implemented on the Hoover database indicate the efficiency of the proposed approach,and this blood vessel segmentation method is better than the Hoover algorithm.

Key words: Gabor filters, mathematical morphology, image enhancement, vessel segmentation

摘要: 针对视网膜血管网络灰度分布特征和区域结构特征,提出了一种基于Gabor小波的视网膜血管提取方法。采用Gabor滤波预处理以增强血管,用改进的自适应二值化方法对增强后的视网膜图像进行二值化处理,根据视网膜血管具有区域连通性的特征,并用形态学方法分割出最终的血管。为验证方法的有效性,对Hoover眼底图像库进行实验,结果表明该方法在细小血管的提取以及连续性、有效性方面都优于Hoover算法。

关键词: Gabor滤波器, 数学形态学, 图像增强, 血管提取