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

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

21 Citaten (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.

Originele taal-2Engels
TitelImage Analysis and Processing — ICIAP 2015
Subtitel18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings, Part 1
RedacteurenVittorio Murino, Enrico Puppo
Plaats van productieBerlin
Aantal pagina's11
ISBN van elektronische versie978-3-319-23231-7
ISBN van geprinte versie978-3-319-23230-0
StatusGepubliceerd - 2015
Evenement18th International Conference on Image Analysis and Processing (ICIAP 2015) - Genoa, Italië
Duur: 7 sep. 201511 sep. 2015
Congresnummer: 18

Publicatie series

NaamLecture Notes in Computer Science
UitgeverijSpringer International Publishing
ISSN van geprinte versie0302-9743
ISSN van elektronische versie16113349


Congres18th International Conference on Image Analysis and Processing (ICIAP 2015)
Verkorte titelICIAP 2015
Internet adres


Duik in de onderzoeksthema's van 'Robust and fast vessel segmentation via Gaussian derivatives in orientation scores'. Samen vormen ze een unieke vingerafdruk.

Citeer dit