Blur detection in fundus images

The paper addresses the problem of retinal image quality assessment, in particular the problem of blur detection for retinal images is considered. The blur value is obtained using an analysis of blood vessel edge widths as the vasculature is the object that is least prone to structural distortion ev...

Full description

Saved in:
Bibliographic Details
Published in2012 5th International Conference on Biomedical Engineering and Informatics pp. 243 - 246
Main Authors Chernomorets, Alexandra A., Krylov, Andrey S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2012
Online AccessGet full text

Cover

More Information
Summary:The paper addresses the problem of retinal image quality assessment, in particular the problem of blur detection for retinal images is considered. The blur value is obtained using an analysis of blood vessel edge widths as the vasculature is the object that is least prone to structural distortion even if blurred. The paper presents the model of a general edge based on the Gaussian filtering and also the paper presents the algorithm for edge width estimation. The values of the parameters for the algorithm are chosen according to experiments on synthetic data.
ISBN:9781467311830
1467311839
DOI:10.1109/BMEI.2012.6513030