Segmenting retinal blood vessels with gabor filter and automatic binarization

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

For timely diagnosis of retinal disease, routine retinal monitoring of people with high risk should be put in place. To assist the ophthalmologists in performing retinal analysis efficiently and accurately, numerous studies have been conducted to propose an automated retinal diagnosis system. One of the crucial steps for such a system is accurate detection of retinal blood vessels from retinal image. In this paper, we investigated the use of automatic binarization methods on pre-processed fundus image to detect retinal blood vessels. Three methods for binarization were investigated in this study, namely Otsu's method, ISODATA and K-means clustering method. The resulting binarized output indicated good detection of large vessels but most of the smaller vessels were left undetected. To address this issue, Gabor wavelet filter was used to enhance the small blood vessel structures before binarization of the filter output. Combining the binary images from both binarization with and without Gabor filter resulted in significant improvement of the overall detection rate of the retinal blood vessels. The proposed method proved to be comparable to other unsupervised techniques in the literature when validated using the publicly available fundus image database, DRIVE.

Original languageEnglish
Pages (from-to)163-167
Number of pages5
JournalInternational Journal of Engineering and Technology(UAE)
Volume7
Issue number4
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

Gabor filters
Retinal Vessels
Blood vessels
Binary images
Retinal Diseases
Blood Vessels
Cluster Analysis
Monitoring
Databases

Keywords

  • Binarization
  • Blood vessel
  • Gabor wavelet
  • Retinal image
  • Segmentation

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science (miscellaneous)
  • Environmental Engineering
  • Chemical Engineering(all)
  • Engineering(all)
  • Hardware and Architecture

Cite this

@article{b4ae83a8f7b54e1cadd88c74ec94ff91,
title = "Segmenting retinal blood vessels with gabor filter and automatic binarization",
abstract = "For timely diagnosis of retinal disease, routine retinal monitoring of people with high risk should be put in place. To assist the ophthalmologists in performing retinal analysis efficiently and accurately, numerous studies have been conducted to propose an automated retinal diagnosis system. One of the crucial steps for such a system is accurate detection of retinal blood vessels from retinal image. In this paper, we investigated the use of automatic binarization methods on pre-processed fundus image to detect retinal blood vessels. Three methods for binarization were investigated in this study, namely Otsu's method, ISODATA and K-means clustering method. The resulting binarized output indicated good detection of large vessels but most of the smaller vessels were left undetected. To address this issue, Gabor wavelet filter was used to enhance the small blood vessel structures before binarization of the filter output. Combining the binary images from both binarization with and without Gabor filter resulted in significant improvement of the overall detection rate of the retinal blood vessels. The proposed method proved to be comparable to other unsupervised techniques in the literature when validated using the publicly available fundus image database, DRIVE.",
keywords = "Binarization, Blood vessel, Gabor wavelet, Retinal image, Segmentation",
author = "Aziah Ali and Aini Hussain and {Wan Zaki}, {Wan Mimi Diyana}",
year = "2018",
month = "1",
day = "1",
doi = "10.14419/ijet.v7i4.11.20794",
language = "English",
volume = "7",
pages = "163--167",
journal = "International Journal of Engineering and Technology(UAE)",
issn = "2227-524X",
publisher = "Science Publishing Corporation Inc",
number = "4",

}

TY - JOUR

T1 - Segmenting retinal blood vessels with gabor filter and automatic binarization

AU - Ali, Aziah

AU - Hussain, Aini

AU - Wan Zaki, Wan Mimi Diyana

PY - 2018/1/1

Y1 - 2018/1/1

N2 - For timely diagnosis of retinal disease, routine retinal monitoring of people with high risk should be put in place. To assist the ophthalmologists in performing retinal analysis efficiently and accurately, numerous studies have been conducted to propose an automated retinal diagnosis system. One of the crucial steps for such a system is accurate detection of retinal blood vessels from retinal image. In this paper, we investigated the use of automatic binarization methods on pre-processed fundus image to detect retinal blood vessels. Three methods for binarization were investigated in this study, namely Otsu's method, ISODATA and K-means clustering method. The resulting binarized output indicated good detection of large vessels but most of the smaller vessels were left undetected. To address this issue, Gabor wavelet filter was used to enhance the small blood vessel structures before binarization of the filter output. Combining the binary images from both binarization with and without Gabor filter resulted in significant improvement of the overall detection rate of the retinal blood vessels. The proposed method proved to be comparable to other unsupervised techniques in the literature when validated using the publicly available fundus image database, DRIVE.

AB - For timely diagnosis of retinal disease, routine retinal monitoring of people with high risk should be put in place. To assist the ophthalmologists in performing retinal analysis efficiently and accurately, numerous studies have been conducted to propose an automated retinal diagnosis system. One of the crucial steps for such a system is accurate detection of retinal blood vessels from retinal image. In this paper, we investigated the use of automatic binarization methods on pre-processed fundus image to detect retinal blood vessels. Three methods for binarization were investigated in this study, namely Otsu's method, ISODATA and K-means clustering method. The resulting binarized output indicated good detection of large vessels but most of the smaller vessels were left undetected. To address this issue, Gabor wavelet filter was used to enhance the small blood vessel structures before binarization of the filter output. Combining the binary images from both binarization with and without Gabor filter resulted in significant improvement of the overall detection rate of the retinal blood vessels. The proposed method proved to be comparable to other unsupervised techniques in the literature when validated using the publicly available fundus image database, DRIVE.

KW - Binarization

KW - Blood vessel

KW - Gabor wavelet

KW - Retinal image

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85054374810&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054374810&partnerID=8YFLogxK

U2 - 10.14419/ijet.v7i4.11.20794

DO - 10.14419/ijet.v7i4.11.20794

M3 - Article

AN - SCOPUS:85054374810

VL - 7

SP - 163

EP - 167

JO - International Journal of Engineering and Technology(UAE)

JF - International Journal of Engineering and Technology(UAE)

SN - 2227-524X

IS - 4

ER -