since 05 February 2011 :
View(s): 504 (6 ULiège)
Download(s): 99 (1 ULiège)
print        
Saleh Shahbeig & Mohammad Sadegh Helfroush

A Novel and Efficient Method to Extract Blood Vessels from Retinal Images

(Volume 85 - Année 2016 — Articles)
Article
Open Access

Attached document(s)

original pdf file

Abstract

The retinal images contain vital features which are important in the analysis of the retina for various medical applications or human identification. In this manuscript, an Adaptive Weighted Morphological Functor (AWMF) method is proposed for the extraction of blood vessels. The method considers the dispersion of the blood vessel in various directions in the retinal images with prior knowledge of the approximate direction of the edges. The proposed blood vessels extraction algorithm, using principle component analysis (PCA) technique and estimation of the brightness and contrast of the background, effectively eliminates interference of regions with intense brightness structure from the background light distribution. Then the method selects a proper way to modify the brightness distribution of the background, regardless of the destructive effect of brightness structures such as optical disc (OD). The experimental results indicate that the proposed algorithm achieves an accuracy rate of 97.11% for the blood vessels extraction on the famous databases, DRIVE.

Keywords : adaptive weighted morphological functors, blood vessels, principle component analysis, retinal images, segmentation

To cite this article

Saleh Shahbeig & Mohammad Sadegh Helfroush, «A Novel and Efficient Method to Extract Blood Vessels from Retinal Images», Bulletin de la Société Royale des Sciences de Liège [En ligne], Volume 85 - Année 2016, Articles, 139 - 151 URL : http://popups.ulg.be/0037-9565/index.php?id=5759.

About: Saleh Shahbeig

Young Researchers and Elite Club, Najafabad Branch, Islamic Azad University, Najafabad, Iran, saleh_shahbeig@yahoo.com

About: Mohammad Sadegh Helfroush

Department of Electrical and Electronics Engineering, Shiraz University of Technology, Shiraz, Iran