Biologically-inspired supervised vasculature segmentation in SLO retinal fundus images

S. Abbasi-Sureshjani, I.M. Smit-Ockeloen, J. Zhang, B.M. ter Haar Romenij

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureHoofdstukAcademicpeer review

24 Citaten (Scopus)
1 Downloads (Pure)


We propose a novel Brain-Inspired Multi-Scales and Multi-Orientations (BIMSO) segmentation technique for the retinal images taken with laser ophthalmoscope (SLO) imaging cameras. Conventional retinal segmentation methods have been designed mainly for color RGB images and they often fail in segmenting the SLO images because of the presence of noise in these images. We suppress the noise and enhance the blood vessels by lifting the 2D image to a joint space of positions and orientations (SE(2)) using the directional anisotropic wavelets. Then a neural network classifier is trained and tested using several features including the intensity of pixels, filter response to the wavelet and multi-scale left-invariant Gaussian derivatives jet in SE(2). BIMSO is robust against noise, non-uniform luminosity and contrast variability. In addition to preserving the connections, it has higher sensitivity and detects the small vessels better compared to state-of-the-art methods for both RGB and SLO images.
Originele taal-2Engels
TitelImage Analysis and Recognition
Subtitel12th International Conference, ICIAR 2015, Niagara Falls, ON, Canada, July 22-24, 2015, Proceedings
Plaats van productieBerlin
Aantal pagina's10
ISBN van elektronische versie978-3-319-20801-5
ISBN van geprinte versie978-3-319-20800-8
StatusGepubliceerd - 4 jul 2015
Evenement12th International Conference on Image Analysis and Recognition (ICIAR 2015) - Niagara Falls, Canada
Duur: 22 jul 201524 jul 2015
Congresnummer: 12


Congres12th International Conference on Image Analysis and Recognition (ICIAR 2015)
Verkorte titelICIAR 2015
StadNiagara Falls
Internet adres

Vingerafdruk Duik in de onderzoeksthema's van 'Biologically-inspired supervised vasculature segmentation in SLO retinal fundus images'. Samen vormen ze een unieke vingerafdruk.

Citeer dit