• DocumentCode
    2152753
  • Title

    A method of retinal vessel width measurement

  • Author

    Zhao, Xiaofang ; Duan, Wenwen ; Lin, Tusheng ; Li, Bi

  • Author_Institution
    Sch. of Electron. & Inf., South China Univ. of Technol., Guangzhou, China
  • Volume
    3
  • fYear
    2010
  • fDate
    26-28 Feb. 2010
  • Firstpage
    443
  • Lastpage
    446
  • Abstract
    According to Gaussian model of retinal blood vessel profile, a retinal vessel blood diameter automatic measurement method is proposed based on the gray-scale image. This method does not need segment and binary operation, it directly finds the rough location of the center points of ROI region, which is operated in column and row respectively, and then using the eigenvectors of Hessian matrix to determine the blood vessels radial direction, at last fitting its radial gray values with least-squares. The process is repeated until the central point convergence. Finally the diameter of blood vessel is determined by finding the knee point. To enhance the robustness of the algorithm, the weighted average of five adjacent diameters are used to replace the diameter of the test points. Experimental results show that the method is stable, simple and effective.
  • Keywords
    Hessian matrices; blood vessels; eigenvalues and eigenfunctions; eye; least squares approximations; plethysmography; Gaussian model; Hessian matrix; blood vessel radial direction; center point location; eigenvectors; gray-scale image; knee point; least-squares fitting; retinal blood vessel profile; retinal vessel blood diameter automatic measurement method; retinal vessel width measurement method; Biomedical imaging; Blood vessels; Convergence; Gray-scale; Image segmentation; Knee; Retina; Retinal vessels; Robustness; Testing; Gaussian model; Hessian matrix; Retina; diameter measuremen;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on
  • Conference_Location
    Singapore
  • Print_ISBN
    978-1-4244-5585-0
  • Electronic_ISBN
    978-1-4244-5586-7
  • Type

    conf

  • DOI
    10.1109/ICCAE.2010.5451363
  • Filename
    5451363