Retinal blood vessel segmentation using ensemble of single oriented mask filters

Fauziah Kasmin, Azizi Abdullah, Anton Satria Prabuwono

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper describes a method on segmentation of blood vessel in retinal images using supervised approach. Blood vessel segmentation in retinal images can be used for analyses in diabetic retinopathy automated screening. It is a very exhausting job and took a very long time to segment retinal blood vessels manually. Moreover these tasks also requires training and skills. The strategy involves the applications of Support Vector Machine to classify each pixel whether it belongs to a vessel or not. Single mask filters which consist of intensity values of normalized green channel have been generated according to the direction of angles. These single oriented mask filters contain the vectors of the neighbourhood of each pixel. Five images randomly selected from DRIVE database are used to train the classifier. Every single oriented mask filters are ranked according to the average accuracy of training images and their weights are assigned based on this rank. Ensemble approaches that are Addition With Weight and Product With Weight have been used to combine all these single mask filters. In order to test the proposed approach, two standard databases, DRIVE and STARE have been used. The results of the proposed method clearly show improvement compared to other single oriented mask filters.

Original languageEnglish
Pages (from-to)1414-1422
Number of pages9
JournalInternational Journal of Electrical and Computer Engineering
Volume7
Issue number3
DOIs
Publication statusPublished - 1 Jun 2017

Fingerprint

Blood vessels
Masks
Pixels
Support vector machines
Screening
Classifiers

Keywords

  • Blood vessel segmentation Oriented mask filter
  • Ensemble approaches
  • Neighbourhood
  • Retinal images

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Retinal blood vessel segmentation using ensemble of single oriented mask filters. / Kasmin, Fauziah; Abdullah, Azizi; Prabuwono, Anton Satria.

In: International Journal of Electrical and Computer Engineering, Vol. 7, No. 3, 01.06.2017, p. 1414-1422.

Research output: Contribution to journalArticle

@article{fd206e7b612d4c7bbaea6bf4dda6dd94,
title = "Retinal blood vessel segmentation using ensemble of single oriented mask filters",
abstract = "This paper describes a method on segmentation of blood vessel in retinal images using supervised approach. Blood vessel segmentation in retinal images can be used for analyses in diabetic retinopathy automated screening. It is a very exhausting job and took a very long time to segment retinal blood vessels manually. Moreover these tasks also requires training and skills. The strategy involves the applications of Support Vector Machine to classify each pixel whether it belongs to a vessel or not. Single mask filters which consist of intensity values of normalized green channel have been generated according to the direction of angles. These single oriented mask filters contain the vectors of the neighbourhood of each pixel. Five images randomly selected from DRIVE database are used to train the classifier. Every single oriented mask filters are ranked according to the average accuracy of training images and their weights are assigned based on this rank. Ensemble approaches that are Addition With Weight and Product With Weight have been used to combine all these single mask filters. In order to test the proposed approach, two standard databases, DRIVE and STARE have been used. The results of the proposed method clearly show improvement compared to other single oriented mask filters.",
keywords = "Blood vessel segmentation Oriented mask filter, Ensemble approaches, Neighbourhood, Retinal images",
author = "Fauziah Kasmin and Azizi Abdullah and Prabuwono, {Anton Satria}",
year = "2017",
month = "6",
day = "1",
doi = "10.11591/ijece.v7i3.pp1414-1422",
language = "English",
volume = "7",
pages = "1414--1422",
journal = "International Journal of Electrical and Computer Engineering",
issn = "2088-8708",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "3",

}

TY - JOUR

T1 - Retinal blood vessel segmentation using ensemble of single oriented mask filters

AU - Kasmin, Fauziah

AU - Abdullah, Azizi

AU - Prabuwono, Anton Satria

PY - 2017/6/1

Y1 - 2017/6/1

N2 - This paper describes a method on segmentation of blood vessel in retinal images using supervised approach. Blood vessel segmentation in retinal images can be used for analyses in diabetic retinopathy automated screening. It is a very exhausting job and took a very long time to segment retinal blood vessels manually. Moreover these tasks also requires training and skills. The strategy involves the applications of Support Vector Machine to classify each pixel whether it belongs to a vessel or not. Single mask filters which consist of intensity values of normalized green channel have been generated according to the direction of angles. These single oriented mask filters contain the vectors of the neighbourhood of each pixel. Five images randomly selected from DRIVE database are used to train the classifier. Every single oriented mask filters are ranked according to the average accuracy of training images and their weights are assigned based on this rank. Ensemble approaches that are Addition With Weight and Product With Weight have been used to combine all these single mask filters. In order to test the proposed approach, two standard databases, DRIVE and STARE have been used. The results of the proposed method clearly show improvement compared to other single oriented mask filters.

AB - This paper describes a method on segmentation of blood vessel in retinal images using supervised approach. Blood vessel segmentation in retinal images can be used for analyses in diabetic retinopathy automated screening. It is a very exhausting job and took a very long time to segment retinal blood vessels manually. Moreover these tasks also requires training and skills. The strategy involves the applications of Support Vector Machine to classify each pixel whether it belongs to a vessel or not. Single mask filters which consist of intensity values of normalized green channel have been generated according to the direction of angles. These single oriented mask filters contain the vectors of the neighbourhood of each pixel. Five images randomly selected from DRIVE database are used to train the classifier. Every single oriented mask filters are ranked according to the average accuracy of training images and their weights are assigned based on this rank. Ensemble approaches that are Addition With Weight and Product With Weight have been used to combine all these single mask filters. In order to test the proposed approach, two standard databases, DRIVE and STARE have been used. The results of the proposed method clearly show improvement compared to other single oriented mask filters.

KW - Blood vessel segmentation Oriented mask filter

KW - Ensemble approaches

KW - Neighbourhood

KW - Retinal images

UR - http://www.scopus.com/inward/record.url?scp=85021087906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021087906&partnerID=8YFLogxK

U2 - 10.11591/ijece.v7i3.pp1414-1422

DO - 10.11591/ijece.v7i3.pp1414-1422

M3 - Article

AN - SCOPUS:85021087906

VL - 7

SP - 1414

EP - 1422

JO - International Journal of Electrical and Computer Engineering

JF - International Journal of Electrical and Computer Engineering

SN - 2088-8708

IS - 3

ER -