Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes

Kevin Noronha, Jagadish Nayak, S. N. Bhat

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

Medical image analysis to aid in clinical diagnosis is one of the research areas currently drawing intense interests of scientists and physicians. The retinal fundus photograph are widely used in the diagnosis and treatment of various eye diseases such as Diabetic Retinopathy, glaucoma etc. Diabetic Retinopathy is the leading cause of blindness in the working age population. If the disease is detected and treated early, many of the visual losses can be prevented. This paper describes the methods to detect main features of fundus images such as optic disk, fovea, and exudates and blood vessels. To determine the optic Disk and its centre we find the brightest part of the fundus and apply Hough transform. The candidate region of fovea is defined an area circle. The detection of fovea is done by using its spatial relationship with optic disk. Exudates are found using their high grey level variation and their contours are determined by means of morphological reconstruction techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. AU the enhanced features are then combined in the fundus image for the detection of abnormalities in the eye.

Original languageEnglish
Title of host publication2006 IEEE Region 10 Conference, TENCON 2006
DOIs
Publication statusPublished - 08-08-2007
Externally publishedYes
Event2006 IEEE Region 10 Conference, TENCON 2006 - Hong Kong, China
Duration: 14-11-200617-11-2006

Conference

Conference2006 IEEE Region 10 Conference, TENCON 2006
CountryChina
CityHong Kong
Period14-11-0617-11-06

Fingerprint

Optics
Blood vessels
Hough transforms
Edge detection
Image analysis

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Noronha, K., Nayak, J., & Bhat, S. N. (2007). Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes. In 2006 IEEE Region 10 Conference, TENCON 2006 [4142468] https://doi.org/10.1109/TENCON.2006.343793
Noronha, Kevin ; Nayak, Jagadish ; Bhat, S. N. / Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes. 2006 IEEE Region 10 Conference, TENCON 2006. 2007.
@inproceedings{57ab1e616ea8430d93667dfdebf64447,
title = "Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes",
abstract = "Medical image analysis to aid in clinical diagnosis is one of the research areas currently drawing intense interests of scientists and physicians. The retinal fundus photograph are widely used in the diagnosis and treatment of various eye diseases such as Diabetic Retinopathy, glaucoma etc. Diabetic Retinopathy is the leading cause of blindness in the working age population. If the disease is detected and treated early, many of the visual losses can be prevented. This paper describes the methods to detect main features of fundus images such as optic disk, fovea, and exudates and blood vessels. To determine the optic Disk and its centre we find the brightest part of the fundus and apply Hough transform. The candidate region of fovea is defined an area circle. The detection of fovea is done by using its spatial relationship with optic disk. Exudates are found using their high grey level variation and their contours are determined by means of morphological reconstruction techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. AU the enhanced features are then combined in the fundus image for the detection of abnormalities in the eye.",
author = "Kevin Noronha and Jagadish Nayak and Bhat, {S. N.}",
year = "2007",
month = "8",
day = "8",
doi = "10.1109/TENCON.2006.343793",
language = "English",
isbn = "1424405491",
booktitle = "2006 IEEE Region 10 Conference, TENCON 2006",

}

Noronha, K, Nayak, J & Bhat, SN 2007, Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes. in 2006 IEEE Region 10 Conference, TENCON 2006., 4142468, 2006 IEEE Region 10 Conference, TENCON 2006, Hong Kong, China, 14-11-06. https://doi.org/10.1109/TENCON.2006.343793

Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes. / Noronha, Kevin; Nayak, Jagadish; Bhat, S. N.

2006 IEEE Region 10 Conference, TENCON 2006. 2007. 4142468.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes

AU - Noronha, Kevin

AU - Nayak, Jagadish

AU - Bhat, S. N.

PY - 2007/8/8

Y1 - 2007/8/8

N2 - Medical image analysis to aid in clinical diagnosis is one of the research areas currently drawing intense interests of scientists and physicians. The retinal fundus photograph are widely used in the diagnosis and treatment of various eye diseases such as Diabetic Retinopathy, glaucoma etc. Diabetic Retinopathy is the leading cause of blindness in the working age population. If the disease is detected and treated early, many of the visual losses can be prevented. This paper describes the methods to detect main features of fundus images such as optic disk, fovea, and exudates and blood vessels. To determine the optic Disk and its centre we find the brightest part of the fundus and apply Hough transform. The candidate region of fovea is defined an area circle. The detection of fovea is done by using its spatial relationship with optic disk. Exudates are found using their high grey level variation and their contours are determined by means of morphological reconstruction techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. AU the enhanced features are then combined in the fundus image for the detection of abnormalities in the eye.

AB - Medical image analysis to aid in clinical diagnosis is one of the research areas currently drawing intense interests of scientists and physicians. The retinal fundus photograph are widely used in the diagnosis and treatment of various eye diseases such as Diabetic Retinopathy, glaucoma etc. Diabetic Retinopathy is the leading cause of blindness in the working age population. If the disease is detected and treated early, many of the visual losses can be prevented. This paper describes the methods to detect main features of fundus images such as optic disk, fovea, and exudates and blood vessels. To determine the optic Disk and its centre we find the brightest part of the fundus and apply Hough transform. The candidate region of fovea is defined an area circle. The detection of fovea is done by using its spatial relationship with optic disk. Exudates are found using their high grey level variation and their contours are determined by means of morphological reconstruction techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. AU the enhanced features are then combined in the fundus image for the detection of abnormalities in the eye.

UR - http://www.scopus.com/inward/record.url?scp=34547562438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547562438&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2006.343793

DO - 10.1109/TENCON.2006.343793

M3 - Conference contribution

SN - 1424405491

SN - 9781424405497

BT - 2006 IEEE Region 10 Conference, TENCON 2006

ER -

Noronha K, Nayak J, Bhat SN. Enhancement of retinal fundus Image to highlight the features for detection of abnormal eyes. In 2006 IEEE Region 10 Conference, TENCON 2006. 2007. 4142468 https://doi.org/10.1109/TENCON.2006.343793