Improving the blind restoration of retinal images by means of point-spread-function estimation assessment

0442676 - ÚTIA 2016 RIV US eng C - Conference Paper (international conference)
Marrugo, A. - Millán, M. S. - Šorel, Michal - Kotera, Jan - Šroubek, Filip
Improving the blind restoration of retinal images by means of point-spread-function estimation assessment.
Proceedings of 10th International Seminar on Medical Information Processing and Analysis (SIPAIM) 2014. Washington: SPIE, 2015. SPIE proceedings, 9287. ISBN 978-1-62841-362-5. ISSN 0277-786X.
[International Symposium on Medical Information Processing and Analysis 2014 /10./. Cartagena de Indias (CO), 10.10.2014-16.10.2014]
R&D Projects: GA ČR GA13-29225S
Institutional support: RVO:67985556
Keywords : medical imaging * deconvolution * deblurring
Subject RIV: JD - Computer Applications, Robotics
http://library.utia.cas.cz/separaty/2015/ZOI/sorel-0442676.pdf

Retinal images often suffer from blurring which hinders disease diagnosis and progression assessment. The restoration of the images is carried out by means of blind deconvolution, but the success of the restoration depends on the correct estimation of the point-spread-function (PSF) that blurred the image. The restoration can be space-invariant or space-variant. Because a retinal image has regions without texture or sharp edges, the blind PSF estimation may fail. In this paper we propose a strategy for the correct assessment of PSF estimation in retinal images for restoration by means of space-invariant or space-variant blind deconvolution. Our method is based on a decomposition in Zernike coe cients of the estimated PSFs to identify valid PSFs. This signicantly improves the quality of the image restoration revealed by the increased visibility of small details like small blood vessels and by the lack of restoration artifacts.
Permanent Link: http://hdl.handle.net/11104/0246617