Robust and fast vessel segmentation via Gaussian derivatives in orientation scores

J. Zhang, E. Bekkers, S. Abbasi-Sureshjani, B. Dashtbozorg, B.M ter Haar Romeny

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

23 Citations (Scopus)
4 Downloads (Pure)


We propose a robust and fully automaticmatched filter-based method for retinal vessel segmentation. Different from conventional filters in 2D image domains, we construct a new matched filter based on secondorder Gaussian derivatives in so-called orientation scores, functions on the coupled space of position and orientations ℝ2 ⋊ S1. We lift 2D images to 3D orientation scores by means of a wavelet-type transform using an anisotropic wavelet. In the domain ℝ2 ⋊ S1, we set up rotation and translation invariant second-order Gaussian derivatives. By locally matching the multi-scale second order Gaussian derivative filters with data in orientation scores, we are able to enhance vessel-like structures located in different orientation planes accordingly. Both crossings and tiny vessels are well-preserved due to the proposed multi-scale and multi-orientation filtering method. The proposed method is validated on public databases DRIVE and STARE, and we show that the method is both fast and reliable. With respectively a sensitivity and specificity of 0.7744 and 0.9708 on DRIVE, and 0.7940 and 0.9707 on STARE, our method gives improved performance compared to state-of-the-art algorithms.

Original languageEnglish
Title of host publicationImage Analysis and Processing — ICIAP 2015
Subtitle of host publication18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings, Part 1
EditorsVittorio Murino, Enrico Puppo
Place of PublicationBerlin
Number of pages11
ISBN (Electronic)978-3-319-23231-7
ISBN (Print)978-3-319-23230-0
Publication statusPublished - 2015
Event18th International Conference on Image Analysis and Processing (ICIAP 2015) - Genoa, Italy
Duration: 7 Sept 201511 Sept 2015
Conference number: 18

Publication series

NameLecture Notes in Computer Science
PublisherSpringer International Publishing
ISSN (Print)0302-9743
ISSN (Electronic)16113349


Conference18th International Conference on Image Analysis and Processing (ICIAP 2015)
Abbreviated titleICIAP 2015
Internet address


  • Crossing preservation
  • Gaussian derivatives
  • Matched filter
  • Micro-vasculature
  • Orientation scores
  • Retinal vessel segmentation


Dive into the research topics of 'Robust and fast vessel segmentation via Gaussian derivatives in orientation scores'. Together they form a unique fingerprint.

Cite this