计算机应用 ›› 2011, Vol. 31 ›› Issue (06): 1560-1562.DOI: 10.3724/SP.J.1087.2011.01560

• 图形图像技术 • 上一篇    下一篇

基于Hessian矩阵的多尺度视网膜图像增强方法

游嘉,陈波   

  1. 重庆大学 计算机学院,重庆 400030
  • 收稿日期:2010-12-15 修回日期:2011-02-01 发布日期:2011-06-20 出版日期:2011-06-01
  • 通讯作者: 游嘉
  • 作者简介:游嘉(1985-),女,重庆人,硕士研究生,主要研究方向:医学图像处理、图像融合;
    陈波(1979-),男,重庆人,讲师,博士研究生,主要研究方向:医疗器械、医学图像处理。
  • 基金资助:
    国家科技重大专项;重庆市科技攻关项目;中央高校基本科研业务费资助项目

New approach to retinal image enhancement based on Hessian matrix

YOU Jia,CHEN Bo   

  1. School of Computer Science, Chongqing University, Chongqing 400030, China
  • Received:2010-12-15 Revised:2011-02-01 Online:2011-06-20 Published:2011-06-01
  • Contact: YOU Jia

摘要: 眼底视网膜图像的血管增强在眼科诊断中具有广泛的研究价值。提出了一种基于Hessian矩阵的多尺度血管增强方法,给出了应用的方案和过程,并在DRIVE眼底图像数据库上进行实验。与其他血管增强方法相比,该方案可达到相当的准确率,且在同等准确率下具有较高的鲁棒性。

关键词: 血管增强, Hessian矩阵, 视网膜图像, 多尺度增强滤波

Abstract: The retina vessel enhancement of retina angiography image is considered as an essential factor to improve diagnosis. Therefore, this paper proposed a multi-scale vessel enhancement method for retinal image based on Hessian matrix. Besides, the strategy and process of applying this method were provided. This method was tested on DRIVE database and its results were compared with other methods using the same database. The result shows a considerable accuracy as other methods while obtaining better robustness.

Key words: vascular enhancement, Hessian matrix, retinal image, multi-scale enhancement filtering

中图分类号: