Authors: Alexandre Gonçalves Silva; Fabio Moreira; Marina Silva Fouto; Rangel Arthur; Angélica Moisés Arthur; Yuzo Iano; Jacqueline Mendonça Lopes De Faria
Addresses: Department of Informatics and Statistics, Federal University of Santa Catarina, Florianópolis, Brazil ' Department of Informatics and Statistics, Federal University of Santa Catarina, Florianópolis, Brazil ' Department of Computer Science, Santa Catarina State University, Joinville, Brazil ' Faculty of Technology, University of Campinas, Limeira, Brazil ' Faculty of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil ' Faculty of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil ' Faculty of Medical Sciences, University of Campinas, Campinas, Brazil
Abstract: The quality of retina images is important for the diagnosis and treatment of eye diseases. Blur, distortion, low contrast, among other artifacts, inhibit the viewing of regions of interest. This work proposes a global descriptor based on two extinction values (number of descendants and topological height) for direct analysis of fundus photographs and automatic classification as "good" or "poor" quality. The method does not require any special filtering, image segmentation or internal retina structure location. It is not substantially affected by rotating, resizing or data set type, and is computed in quadratic time. The algorithm achieved an area under ROC curve of 96.13% for UNICAMP, 88.59% for UNIFESP DR2, 99.27% for DRIMDB, and 92.07% for HRF data sets.
Keywords: topological extinction values; ophthalmic imaging; fundus quality assessment; image descriptor.
International Journal of Computer Applications in Technology, 2019 Vol.59 No.3, pp.224 - 235
Received: 27 Jun 2017
Accepted: 19 Feb 2018
Published online: 22 Mar 2019 *