Retinal vessel segmentation using multiwavelet kernels and multiscale hierarchical decomposition

TY - JOUR

T1 - Retinal vessel segmentation using multiwavelet kernels and multiscale hierarchical decomposition

AU - Wang, Yangfan

AU - Ji, Guangrong

AU - Lin, Ping

AU - Trucco, Emanuele

N1 - Copyright 2013 Elsevier B.V., All rights reserved.

PY - 2013/8

Y1 - 2013/8

N2 - We propose a comprehensive method for segmenting the retinal vasculature in fundus camera images. Our method does not require preprocessing and training and can therefore be used directly on different images sets. We enhance the vessels using matched filtering with multiwavelet kernels (MFMK), separating vessels from clutter and bright, localized features. Noise removal and vessel localization are achieved by a multiscale hierarchical decomposition of the normalized enhanced image. We show a necessary condition to achieve the optimal decomposition and derive the associated value of the scale parameter controlling the amount of details captured. Finally, we obtain a binary map of the vasculature by locally adaptive thresholding, generating a threshold surface based on the vessel edge information extracted by the previous processes. We report experimental results on two public retinal data sets, DRIVE and STARE, demonstrating an excellent performance in comparison with retinal vessel segmentation methods reported recently.

AB - We propose a comprehensive method for segmenting the retinal vasculature in fundus camera images. Our method does not require preprocessing and training and can therefore be used directly on different images sets. We enhance the vessels using matched filtering with multiwavelet kernels (MFMK), separating vessels from clutter and bright, localized features. Noise removal and vessel localization are achieved by a multiscale hierarchical decomposition of the normalized enhanced image. We show a necessary condition to achieve the optimal decomposition and derive the associated value of the scale parameter controlling the amount of details captured. Finally, we obtain a binary map of the vasculature by locally adaptive thresholding, generating a threshold surface based on the vessel edge information extracted by the previous processes. We report experimental results on two public retinal data sets, DRIVE and STARE, demonstrating an excellent performance in comparison with retinal vessel segmentation methods reported recently.

UR - https://www.scopus.com/pages/publications/84875719608

U2 - 10.1016/j.patcog.2012.12.014

DO - 10.1016/j.patcog.2012.12.014

M3 - Article

AN - SCOPUS:84875719608

SN - 0031-3203

VL - 46

SP - 2117

EP - 2133

JO - Pattern Recognition

JF - Pattern Recognition

IS - 8

ER -