Detail výsledku
Symptoms Detection in Eye Retina Image
Maruniak Lukáš, Ing., FIT (FIT)
Drahanský Martin, prof. Ing., Ph.D., UITS (FIT)
Diabetic retinopathy and age related macular degeneration are among the most common eye retina diseases, which cause partial or complete blindness. The purpose of this study is to design and implement software for automatic detection of symptoms from eye fundus images. The detection algorithm is based on segmentation methods and follow up analysis of segmented areas. Detection of retina objects such as optic disc, macula and blood vessels is important prior symptoms detection as they can adversely affect the results of the analysis. Total 259 images of four databases were analyzed and algorithm reaches more than 90 % average success rate. The software might be useful in combination with appropriate hardware and optic devices, and can find a practical application in global population screening.
eye retina, symptoma, macula, optic disc, segmentation
@inproceedings{BUT144476,
author="Daniel {Koštialik} and Lukáš {Maruniak} and Martin {Drahanský}",
title="Symptoms Detection in Eye Retina Image",
booktitle="2017 IEEE Symposium Series on Computational Intelligence",
year="2018",
pages="1--6",
publisher="IEEE Computer Society",
address="Hawaii",
doi="10.1109/SSCI.2017.8285165",
isbn="978-1-5386-2725-9",
url="https://www.fit.vut.cz/research/publication/11531/"
}