Automated identification of exudates and optic disc based on inverse surface thresholding

Haniza Yazid, Hamzah Arof, Hazlita Mohd Isa

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms a method based on watershed segmentation.

Original languageEnglish
Pages (from-to)1997-2004
Number of pages8
JournalJournal of Medical Systems
Volume36
Issue number3
DOIs
Publication statusPublished - Jun 2012

Fingerprint

Optic Disk
Exudates and Transudates
Optics
Databases
Edge detection
Watersheds
Cluster Analysis
Color

Keywords

  • Biomedical applications
  • Diabetic retinopathy
  • Exudates
  • Inverse surface thresholding

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Health Informatics
  • Health Information Management
  • Information Systems

Cite this

Automated identification of exudates and optic disc based on inverse surface thresholding. / Yazid, Haniza; Arof, Hamzah; Mohd Isa, Hazlita.

In: Journal of Medical Systems, Vol. 36, No. 3, 06.2012, p. 1997-2004.

Research output: Contribution to journalArticle

@article{9833e33caf3545b9bcaa39f8efb6d740,
title = "Automated identification of exudates and optic disc based on inverse surface thresholding",
abstract = "This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms a method based on watershed segmentation.",
keywords = "Biomedical applications, Diabetic retinopathy, Exudates, Inverse surface thresholding",
author = "Haniza Yazid and Hamzah Arof and {Mohd Isa}, Hazlita",
year = "2012",
month = "6",
doi = "10.1007/s10916-011-9659-4",
language = "English",
volume = "36",
pages = "1997--2004",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Automated identification of exudates and optic disc based on inverse surface thresholding

AU - Yazid, Haniza

AU - Arof, Hamzah

AU - Mohd Isa, Hazlita

PY - 2012/6

Y1 - 2012/6

N2 - This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms a method based on watershed segmentation.

AB - This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms a method based on watershed segmentation.

KW - Biomedical applications

KW - Diabetic retinopathy

KW - Exudates

KW - Inverse surface thresholding

UR - http://www.scopus.com/inward/record.url?scp=84863756556&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863756556&partnerID=8YFLogxK

U2 - 10.1007/s10916-011-9659-4

DO - 10.1007/s10916-011-9659-4

M3 - Article

VL - 36

SP - 1997

EP - 2004

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 3

ER -