Browsing by Author "Millan M.S."

Now showing 1 - 3 of 3

Blind restoration of retinal images degraded by space-variant blur with adaptive blur estimation
(2013) Marrugo A.G.; Millan M.S.; Sorel M.; Sroubek F.
Retinal images are often degraded with a blur that varies across the gield view. Because traditional deblurring algorithms assume the blur to be space-invariant they typically fail in the presence of space-variant blur. In this work we consider the blur to be both unknown and space-variant. To carry out the restoration, we assume that in small regions the space-variant blur can be approximated by a space-invariant point-spread function (PSF). However, instead of deblurring the image on a per-patch basis, we extend individual PSFs by linear interpolation and perform a global restoration. Because the blind estimation of local PSFs may fail we propose a strategy for the identification of valid local PSFs and perform interpolation to obtain the space-variant PSF. The method was tested on artificial and real degraded retinal images. Results show significant improvement in the visibility of subtle details like small blood vessels. © 2013 SPIE.
Implementation of an image based focusing algorithm for non-mydriatic retinal imaging
(Institute of Electrical and Electronics Engineers Inc., 2014) Marrugo A.G.; Millan M.S.; Abril H.C.; Marrugo A.G.
Retinal photography is important for the assessment of eye diseases. The task of fine focusing the image is demanding and lack of focus is often the cause of suboptimal photographs. The advent of digital cameras has provided the opportunity to automate the focusing process. In this work, we propose an auto-focus system for non-mydriatic retinal imaging. The core of the system is based on a robust image-based focus measure. The measure is basically a quantification of image anisotropy computed by means of the normalized discrete cosine transform. Additionally, we optimize the autofocusing method by evaluating different focus search strategies. Encouraging experimental results reveal that the method is able to identify the best focus reliably with optimal speed. © 2014 IEEE.
On the compensation of uneven illumination in retinal images for restoration by means of blind deconvolution
(Institute of Electrical and Electronics Engineers Inc., 2016) Marrugo A.G.; Vargas R.; Contreras Ortiz, Sonia Helena; Millan M.S.; Altuve M.
Retinal eye fundus images are used for diagnostic purposes, but despite controlled conditions in acquisition they often suffer from uneven illumination and blur. In this work, we propose the use of multi-channel blind deconvolution for the restoration of blurred retinal images. The estimation of an adequate point-spread function (PSF) is highly dependent on the registration of at least two images from the same retina, which undergo illumination compensation. We use the bi-dimensional empirical mode decomposition (BEMD) approach to model the illumination distribution as a sum of non-stationary signals. The BEMD approach enables an artifact-free compensation of the illumination in order to estimate an adequate PSF and carry out the best restoration possible. Encouraging experimental results show significant enhancement in the retinal images with increased contrast and visibility of subtle details like small blood vessels. © 2016 IEEE.