Number of the records: 1  

Restoration of retinal images with space-variant blur

  1. 1.
    SYSNO ASEP0424586
    Document TypeJ - Journal Article
    R&D Document TypeJournal Article
    Subsidiary JČlánek ve WOS
    TitleRestoration of retinal images with space-variant blur
    Author(s) Marrugo, A. (ES)
    Millán, M. S. (ES)
    Šorel, Michal (UTIA-B) RID
    Šroubek, Filip (UTIA-B) RID
    Source TitleJournal of Biomedical Optics - ISSN 1083-3668
    Roč. 19, č. 1 (2014), 016023-1-016023-12
    Number of pages12 s.
    Publication formPrint - P
    Languageeng - English
    CountryUS - United States
    Keywordsblind deconvolution ; space-variant restoration ; retinal image
    Subject RIVJD - Computer Applications, Robotics
    R&D ProjectsGA13-29225S GA ČR - Czech Science Foundation (CSF)
    Institutional supportUTIA-B - RVO:67985556
    UT WOS000331892700055
    EID SCOPUS84897748145
    DOI10.1117/1.JBO.19.1.016023
    AnnotationRetinal images are essential clinical resources for the diagnosis of retinopathy and many other ocular diseases. Because of improper acquisition conditions or inherent optical aberrations in the eye, the images are often degraded with blur. In many common cases, the blur varies across the field of view. Most image deblurring algorithms assume a space-invariant blur, which fails in the presence of space-variant (SV) blur. In this work, we propose an innovative strategy for the restoration of retinal images in which we consider the blur to be both unknown and SV. We model the blur by a linear operation interpreted as a convolution with a point-spread function (PSF) that changes with the position in the image. To achieve an artifact-free restoration, we propose a framework for a robust estimation of the SV PSF based on an eye-domain knowledge strategy. The restoration method was tested on artificially and naturally degraded retinal images. The results show an important enhance- ment, significant enough to leverage the images’ clinical use
    WorkplaceInstitute of Information Theory and Automation
    ContactMarkéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
    Year of Publishing2015
Number of the records: 1