Three-stages hard exudates segmentation in retinal images

Kusakunniran, W; Wul, Q; Ritthipravad, P; Zhang, J

Three-stages hard exudates segmentation in retinal images

Kusakunniran, W Wul, Q Ritthipravad, P Zhang, J

Permalink

Publication Type:: Conference Proceeding
Citation:: 2017 9th International Conference on Information Technology and Electrical Engineering, ICITEE 2017, 2017, 2018-January pp. 1 - 6
Issue Date:: 2017-07-01

Closed Access

	Filename	Description	Size
	08250438.pdf	Published version	565.7 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Kusakunniran, W	en_US
dc.contributor.author	Wul, Q	en_US
dc.contributor.author	Ritthipravad, P	en_US
dc.contributor.author	Zhang, J https://orcid.org/0000-0002-7240-3541	en_US
dc.date.issued	2017-07-01	en_US
dc.identifier.citation	2017 9th International Conference on Information Technology and Electrical Engineering, ICITEE 2017, 2017, 2018-January pp. 1 - 6	en_US
dc.identifier.isbn	9781509064779	en_US
dc.identifier.uri	http://hdl.handle.net/10453/126899
dc.description.abstract	© 2017 IEEE. This paper proposes a three-stages method of hard exudate segmentation in retinal images. The first stage is the pre-processing. The color transfer is applied to make all retinal images to have the same color characteristics, based on statistical analysis. Then, only a yellow channel of each image is used in the further analysis. The second stage is the blob initialization. The blob detection based on color, size, and shape including circularity and convexity is used to identify initial pixels of hard exudates. The detected blobs must not be inside the optic disk. The third stage is the segmentation. The graph cut is iteratively applied on partitions of the image. The fine-tune segmentation in sub-images is necessary because the portion of hard exudates is significantly less than the portion of non-hard exudates. The proposed method is evaluated using the two well-known datasets, namely e-ophtha and DIARETDB1, in both aspects of pixel-level and image-level. Based on the comprehensive comparisons with the existing works, the proposed method is shown to be very promising. In the image-level, it achieves 96% sensitivity and 94% specificity for the e-ophtha dataset, and 96% sensitivity and 98% specificity for the DIARETDB1 dataset.	en_US
dc.relation.ispartof	2017 9th International Conference on Information Technology and Electrical Engineering, ICITEE 2017	en_US
dc.relation.isbasedon	10.1109/ICITEED.2017.8250438	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Three-stages hard exudates segmentation in retinal images	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-January	en_US
utslib.for	1113 Opthalmology and Optometry	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
utslib.copyright.status	closed_access	*
pubs.publication-status	Published	en_US
pubs.volume	2018-January	en_US

Abstract:

© 2017 IEEE. This paper proposes a three-stages method of hard exudate segmentation in retinal images. The first stage is the pre-processing. The color transfer is applied to make all retinal images to have the same color characteristics, based on statistical analysis. Then, only a yellow channel of each image is used in the further analysis. The second stage is the blob initialization. The blob detection based on color, size, and shape including circularity and convexity is used to identify initial pixels of hard exudates. The detected blobs must not be inside the optic disk. The third stage is the segmentation. The graph cut is iteratively applied on partitions of the image. The fine-tune segmentation in sub-images is necessary because the portion of hard exudates is significantly less than the portion of non-hard exudates. The proposed method is evaluated using the two well-known datasets, namely e-ophtha and DIARETDB1, in both aspects of pixel-level and image-level. Based on the comprehensive comparisons with the existing works, the proposed method is shown to be very promising. In the image-level, it achieves 96% sensitivity and 94% specificity for the e-ophtha dataset, and 96% sensitivity and 98% specificity for the DIARETDB1 dataset.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/126899