Multi-scale approach for retinal vessel segmentation using medialness function

Elahe Moghimirad, Seyed Hamid Rezatofighi, Hamid Soltanian-Zadeh

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

9 Citations (Scopus)


Automated segmentation of retinal vessels in optic fundus images has been the most prevailing effort in many researches during recent years. In this paper, we propose a multi-scale method based on a weighted 2D medialness function. The result of the medialness function is first multiplied by the eigenvalues of the Hessian matrix in every pixel of the image in order to extract vessel's medial-lines. Next, by extracting the centerlines of vessels and estimation of radius of vessels, the retinal vessels are segmented. Finally, the performance of our proposed method is evaluated by the DRIVE and STARE databases and compared with those of several recent methods.

Original languageEnglish
Title of host publication2010 7th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2010 - Proceedings
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Print)9781424441266
Publication statusPublished - 2010
Externally publishedYes
EventIEEE International Symposium on Biomedical Imaging 2010: From Nano to Macro - Rotterdam, Netherlands
Duration: 14 Apr 201017 Apr 2010
Conference number: 7th


ConferenceIEEE International Symposium on Biomedical Imaging 2010
Abbreviated title ISBI 2010


  • Eigenvalue
  • Medialness function
  • Radius estimation
  • Retinal vessel segmentation

Cite this