Abstract
Automatic detection of optic disc and fovea is a precursor to the computer-aided analysis of retinal pathologies. In this paper, we present a unified approach for optic disc and fovea detection based on normalized cross-correlation technique. The algorithm performance is optimized by introducing vector inner products and norms instead of conventional mean and variance computations. We report optic disc detection results on four publicly available fundus image databases amounting to a total of 1451 fundus images and fovea detection results on another four publicly available fundus image databases amounting to a total of 1454 fundus images. The proposed method results in an optic disc detection accuracy of 99.01%, 95.67%, 99.09%, and 100% on DRISHTI-GS, MESSIDOR, DRIONS-DB, and DRIVE fundus image databases, respectively, and fovea detection accuracy of 94.83%, 84.62%, 95.51%, and 97.14% on MESSIDOR, DIARETDB0, DIARETDB1, and DRIVE fundus image databases, respectively. The speed of optic disc and fovea detection has been improved considerably by downsampling technique. In addition, we report the effect of downsampling on the detection accuracy.
| Original language | English |
|---|---|
| Title of host publication | TENCON 2017 - 2017 IEEE Region 10 Conference |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 19-24 |
| Number of pages | 6 |
| Volume | 2017-December |
| ISBN (Electronic) | 9781509011339 |
| DOIs | |
| Publication status | Published - 19-12-2017 |
| Event | 2017 IEEE Region 10 Conference, TENCON 2017 - Penang, Malaysia Duration: 05-11-2017 → 08-11-2017 |
Conference
| Conference | 2017 IEEE Region 10 Conference, TENCON 2017 |
|---|---|
| Country | Malaysia |
| City | Penang |
| Period | 05-11-17 → 08-11-17 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Electrical and Electronic Engineering
Cite this
}
A unified approach for detection of diagnostically significant regions-of-interest in retinal fundus images. / Kumar, J. R.Harish; Sachi, Simran; Chaudhury, Kunaljit; Harsha, S.; Singh, Birendra Kumar.
TENCON 2017 - 2017 IEEE Region 10 Conference. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. p. 19-24.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - A unified approach for detection of diagnostically significant regions-of-interest in retinal fundus images
AU - Kumar, J. R.Harish
AU - Sachi, Simran
AU - Chaudhury, Kunaljit
AU - Harsha, S.
AU - Singh, Birendra Kumar
PY - 2017/12/19
Y1 - 2017/12/19
N2 - Automatic detection of optic disc and fovea is a precursor to the computer-aided analysis of retinal pathologies. In this paper, we present a unified approach for optic disc and fovea detection based on normalized cross-correlation technique. The algorithm performance is optimized by introducing vector inner products and norms instead of conventional mean and variance computations. We report optic disc detection results on four publicly available fundus image databases amounting to a total of 1451 fundus images and fovea detection results on another four publicly available fundus image databases amounting to a total of 1454 fundus images. The proposed method results in an optic disc detection accuracy of 99.01%, 95.67%, 99.09%, and 100% on DRISHTI-GS, MESSIDOR, DRIONS-DB, and DRIVE fundus image databases, respectively, and fovea detection accuracy of 94.83%, 84.62%, 95.51%, and 97.14% on MESSIDOR, DIARETDB0, DIARETDB1, and DRIVE fundus image databases, respectively. The speed of optic disc and fovea detection has been improved considerably by downsampling technique. In addition, we report the effect of downsampling on the detection accuracy.
AB - Automatic detection of optic disc and fovea is a precursor to the computer-aided analysis of retinal pathologies. In this paper, we present a unified approach for optic disc and fovea detection based on normalized cross-correlation technique. The algorithm performance is optimized by introducing vector inner products and norms instead of conventional mean and variance computations. We report optic disc detection results on four publicly available fundus image databases amounting to a total of 1451 fundus images and fovea detection results on another four publicly available fundus image databases amounting to a total of 1454 fundus images. The proposed method results in an optic disc detection accuracy of 99.01%, 95.67%, 99.09%, and 100% on DRISHTI-GS, MESSIDOR, DRIONS-DB, and DRIVE fundus image databases, respectively, and fovea detection accuracy of 94.83%, 84.62%, 95.51%, and 97.14% on MESSIDOR, DIARETDB0, DIARETDB1, and DRIVE fundus image databases, respectively. The speed of optic disc and fovea detection has been improved considerably by downsampling technique. In addition, we report the effect of downsampling on the detection accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85044214063&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044214063&partnerID=8YFLogxK
U2 - 10.1109/TENCON.2017.8227829
DO - 10.1109/TENCON.2017.8227829
M3 - Conference contribution
VL - 2017-December
SP - 19
EP - 24
BT - TENCON 2017 - 2017 IEEE Region 10 Conference
PB - Institute of Electrical and Electronics Engineers Inc.
ER -