Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
SENGAR, N. DUTTA, M. BURGET, R. RAJNOHA, M.
Originální název
Automated Detection of Suspected Glaucoma in Digital Fundus Images
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
A method is proposed using image processing techniques, which is an automated method for detection of suspected glaucoma. In this paper an algorithm is proposed to detect suspected glaucoma by using the presence or absence of hemorrhages in a particular region, near the optic disc, in fundus image. Unlike existing methods, which only uses cup to disc ratio as a deciding parameter to detect glaucoma, method proposed in this paper helps to diagnose the case of suspected glaucoma efficiently. The optic disc and hemorrhages are segmented in a particular region automatically by using adaptive thresholding and some geometrical features. In existing methods, the majority of work is based on diagnosis of glaucoma, but rarely on suspected glaucoma. So, the proposed method can helpful to diagnose the cases of suspected glaucoma. The proposed algorithm achieves accuracy of 93.57% on digital fundus images for detection of suspected glaucoma.
Klíčová slova
Suspected Glaucoma; Hemorrhages; fundus Image
Autoři
SENGAR, N.; DUTTA, M.; BURGET, R.; RAJNOHA, M.
Vydáno
6. 7. 2017
Místo
Barcelona
ISBN
978-1-5090-3981-4
Kniha
40th Anniversary of International Conference on Telecommunications and Signal Processing (TSP)
Strany od
749
Strany do
752
Strany počet
4
URL
https://ieeexplore.ieee.org/document/8076088
BibTex
@inproceedings{BUT137771, author="Namita {Sengar} and Malay Kishore {Dutta} and Radim {Burget} and Martin {Rajnoha}", title="Automated Detection of Suspected Glaucoma in Digital Fundus Images", booktitle="40th Anniversary of International Conference on Telecommunications and Signal Processing (TSP)", year="2017", pages="749--752", address="Barcelona", doi="10.1109/TSP.2017.8076088", isbn="978-1-5090-3981-4", url="https://ieeexplore.ieee.org/document/8076088" }