Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet

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

Abstract

This paper presents a new unsupervised method for segmenting blood vessels in digital retinal images. The proposed method uses K-means clustering to binarize grayscale vessel-enhanced images derived from green channel image and Gabor wavelet feature image. The binary images are then combined using logical OR to produce segmented vessels. The method was evaluated on the publicly available DRIVE database and the results compared to published literature. The method proved to have comparable performance to other published unsupervised methods while being simple and fast to implement. In the future, the proposed method can be further improved to be applied in real clinical setting to assist the physicians in diagnosing ocular diseases through an automated screening system.

LanguageEnglish
Title of host publicationApplied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016
PublisherSpringer Verlag
Pages221-227
Number of pages7
Volume428
ISBN (Print)9783319539331
DOIs
StatePublished - 2018
Event1st International Conference on Applied Physics, System Science and Computers, APSAC 2016 - Dubrovnik, Croatia
Duration: 28 Sep 201630 Sep 2016

Publication series

NameLecture Notes in Electrical Engineering
Volume428
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other1st International Conference on Applied Physics, System Science and Computers, APSAC 2016
CountryCroatia
CityDubrovnik
Period28/9/1630/9/16

Fingerprint

Binary images
Blood vessels
Screening
Color

Keywords

  • Blood vessel segmentation
  • Gabor wavelet
  • K-means clustering
  • Retinal image

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Ali, A., Wan Zaki, W. M. D., & Hussain, A. (2018). Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet. In Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016 (Vol. 428, pp. 221-227). (Lecture Notes in Electrical Engineering; Vol. 428). Springer Verlag. DOI: 10.1007/978-3-319-53934-8_27

Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet. / Ali, Aziah; Wan Zaki, Wan Mimi Diyana; Hussain, Aini.

Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016. Vol. 428 Springer Verlag, 2018. p. 221-227 (Lecture Notes in Electrical Engineering; Vol. 428).

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

Ali, A, Wan Zaki, WMD & Hussain, A 2018, Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet. in Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016. vol. 428, Lecture Notes in Electrical Engineering, vol. 428, Springer Verlag, pp. 221-227, 1st International Conference on Applied Physics, System Science and Computers, APSAC 2016, Dubrovnik, Croatia, 28/9/16. DOI: 10.1007/978-3-319-53934-8_27
Ali A, Wan Zaki WMD, Hussain A. Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet. In Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016. Vol. 428. Springer Verlag. 2018. p. 221-227. (Lecture Notes in Electrical Engineering). Available from, DOI: 10.1007/978-3-319-53934-8_27
Ali, Aziah ; Wan Zaki, Wan Mimi Diyana ; Hussain, Aini. / Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet. Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016. Vol. 428 Springer Verlag, 2018. pp. 221-227 (Lecture Notes in Electrical Engineering).
@inproceedings{ff2a67a77c17460794499413d919e3b5,
title = "Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet",
abstract = "This paper presents a new unsupervised method for segmenting blood vessels in digital retinal images. The proposed method uses K-means clustering to binarize grayscale vessel-enhanced images derived from green channel image and Gabor wavelet feature image. The binary images are then combined using logical OR to produce segmented vessels. The method was evaluated on the publicly available DRIVE database and the results compared to published literature. The method proved to have comparable performance to other published unsupervised methods while being simple and fast to implement. In the future, the proposed method can be further improved to be applied in real clinical setting to assist the physicians in diagnosing ocular diseases through an automated screening system.",
keywords = "Blood vessel segmentation, Gabor wavelet, K-means clustering, Retinal image",
author = "Aziah Ali and {Wan Zaki}, {Wan Mimi Diyana} and Aini Hussain",
year = "2018",
doi = "10.1007/978-3-319-53934-8_27",
language = "English",
isbn = "9783319539331",
volume = "428",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "221--227",
booktitle = "Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016",
address = "Germany",

}

TY - GEN

T1 - Blood vessel segmentation from color retinal images using K-means clustering and 2D gabor wavelet

AU - Ali,Aziah

AU - Wan Zaki,Wan Mimi Diyana

AU - Hussain,Aini

PY - 2018

Y1 - 2018

N2 - This paper presents a new unsupervised method for segmenting blood vessels in digital retinal images. The proposed method uses K-means clustering to binarize grayscale vessel-enhanced images derived from green channel image and Gabor wavelet feature image. The binary images are then combined using logical OR to produce segmented vessels. The method was evaluated on the publicly available DRIVE database and the results compared to published literature. The method proved to have comparable performance to other published unsupervised methods while being simple and fast to implement. In the future, the proposed method can be further improved to be applied in real clinical setting to assist the physicians in diagnosing ocular diseases through an automated screening system.

AB - This paper presents a new unsupervised method for segmenting blood vessels in digital retinal images. The proposed method uses K-means clustering to binarize grayscale vessel-enhanced images derived from green channel image and Gabor wavelet feature image. The binary images are then combined using logical OR to produce segmented vessels. The method was evaluated on the publicly available DRIVE database and the results compared to published literature. The method proved to have comparable performance to other published unsupervised methods while being simple and fast to implement. In the future, the proposed method can be further improved to be applied in real clinical setting to assist the physicians in diagnosing ocular diseases through an automated screening system.

KW - Blood vessel segmentation

KW - Gabor wavelet

KW - K-means clustering

KW - Retinal image

UR - http://www.scopus.com/inward/record.url?scp=85026789211&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026789211&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-53934-8_27

DO - 10.1007/978-3-319-53934-8_27

M3 - Conference contribution

SN - 9783319539331

VL - 428

T3 - Lecture Notes in Electrical Engineering

SP - 221

EP - 227

BT - Applied Physics, System Science and Computers - Proceedings of the 1st International Conference on Applied Physics, System Science and Computers, APSAC2016

PB - Springer Verlag

ER -