TY - GEN
T1 - ACHIKO-I retinal fundus image database and its evaluation on cup-to-disc ratio measurement
AU - Yin, Fengshou
AU - Liu, Jiang
AU - Wong, Damon Wing Kee
AU - Tan, Ngan Meng
AU - Lee, Beng Hai
AU - Cheng, Jun
AU - Htoo, Min Thet
AU - Zhang, Zhuo
AU - Xu, Yanwu
AU - Gao, Xinting
AU - Srivastava, Ruchir
N1 - Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2013
Y1 - 2013
N2 - Retinal fundus image is a widely used image modality to diagnose ocular diseases such as glaucoma, age-related macular degeneration and diabetic retinopathy. There are a number of fundus image databases available online. However, most of them are used for blood vessel extraction and optic disc localization, and hardly any have optic cup annotation. In this paper, we present a fundus image database with accurate annotation of both the optic disc and optic cup. Besides, there are multiple images for the same subject, taking under different conditions, allowing repeatability study of automated segmentation algorithms. Currently, ACHIKO-I contains 179 images and is divided into two subsets for different purposes. The database is used to evaluate our work on cup-to-disc ratio (CDR) measurement, which also demonstrates how the database can be used and assessed.
AB - Retinal fundus image is a widely used image modality to diagnose ocular diseases such as glaucoma, age-related macular degeneration and diabetic retinopathy. There are a number of fundus image databases available online. However, most of them are used for blood vessel extraction and optic disc localization, and hardly any have optic cup annotation. In this paper, we present a fundus image database with accurate annotation of both the optic disc and optic cup. Besides, there are multiple images for the same subject, taking under different conditions, allowing repeatability study of automated segmentation algorithms. Currently, ACHIKO-I contains 179 images and is divided into two subsets for different purposes. The database is used to evaluate our work on cup-to-disc ratio (CDR) measurement, which also demonstrates how the database can be used and assessed.
UR - http://www.scopus.com/inward/record.url?scp=84881394714&partnerID=8YFLogxK
U2 - 10.1109/ICIEA.2013.6566370
DO - 10.1109/ICIEA.2013.6566370
M3 - Conference contribution
AN - SCOPUS:84881394714
SN - 9781467363211
T3 - Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013
SP - 224
EP - 227
BT - Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013
T2 - 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013
Y2 - 19 June 2013 through 21 June 2013
ER -
