Exudates segmentation using inverse surface adaptive thresholding
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 prop...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2012
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/10291/1/Exudates_segmentation_using_inverse_surface_adaptive_thresholding.pdf |
_version_ | 1796946051302686720 |
---|---|
author | Yazid, Haniza Arof, Hamzah Mohd Isa, Hazlita |
author_facet | Yazid, Haniza Arof, Hamzah Mohd Isa, Hazlita |
author_sort | Yazid, Haniza |
collection | UM |
description | 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 methods based on watershed segmentation and morphological reconstruction. The proposed method obtained 98.2 and 90.4 in terms of sensitivity for Standard Diabetic Retinopathy Database – Calibration Level 1 (DIARETDB1) and a local dataset provided by National University Hospital of Malaysia(NUHM), respectively. |
first_indexed | 2024-03-06T05:25:48Z |
format | Article |
id | um.eprints-10291 |
institution | Universiti Malaya |
language | English |
last_indexed | 2024-03-06T05:25:48Z |
publishDate | 2012 |
publisher | Elsevier |
record_format | dspace |
spelling | um.eprints-102912018-10-11T04:06:07Z http://eprints.um.edu.my/10291/ Exudates segmentation using inverse surface adaptive thresholding Yazid, Haniza Arof, Hamzah Mohd Isa, Hazlita TA Engineering (General). Civil engineering (General) 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 methods based on watershed segmentation and morphological reconstruction. The proposed method obtained 98.2 and 90.4 in terms of sensitivity for Standard Diabetic Retinopathy Database – Calibration Level 1 (DIARETDB1) and a local dataset provided by National University Hospital of Malaysia(NUHM), respectively. Elsevier 2012 Article PeerReviewed application/pdf en http://eprints.um.edu.my/10291/1/Exudates_segmentation_using_inverse_surface_adaptive_thresholding.pdf Yazid, Haniza and Arof, Hamzah and Mohd Isa, Hazlita (2012) Exudates segmentation using inverse surface adaptive thresholding. Measurement, 45. pp. 1599-1608. ISSN 0263-2241, |
spellingShingle | TA Engineering (General). Civil engineering (General) Yazid, Haniza Arof, Hamzah Mohd Isa, Hazlita Exudates segmentation using inverse surface adaptive thresholding |
title | Exudates segmentation using inverse surface adaptive thresholding |
title_full | Exudates segmentation using inverse surface adaptive thresholding |
title_fullStr | Exudates segmentation using inverse surface adaptive thresholding |
title_full_unstemmed | Exudates segmentation using inverse surface adaptive thresholding |
title_short | Exudates segmentation using inverse surface adaptive thresholding |
title_sort | exudates segmentation using inverse surface adaptive thresholding |
topic | TA Engineering (General). Civil engineering (General) |
url | http://eprints.um.edu.my/10291/1/Exudates_segmentation_using_inverse_surface_adaptive_thresholding.pdf |
work_keys_str_mv | AT yazidhaniza exudatessegmentationusinginversesurfaceadaptivethresholding AT arofhamzah exudatessegmentationusinginversesurfaceadaptivethresholding AT mohdisahazlita exudatessegmentationusinginversesurfaceadaptivethresholding |