Machine Learning Approach For Accurate Segmentation Of Blood Vessels In Fundus Images
Author(s):
S.Hemamalini, ALLI.SIVANI, GUNDLURU.SAI MEGHANA REDDY , PENUBARTHI.KUSUMA
Keywords:
diabetic retinopathy; blood vessel extraction; peak detection; valley detection
Abstract
Blood vessel segmentation is the necessary basis while developing retinal screening systems since vessels serve as one of the main retinal attraction features. Medical diagnostics has been drastically improved by the introduction of digital imagery, primarily because of the powerful digital image processing tools. Digital retinal images are used for diagnostics of various diseases containing diabetes, hypertension, stroke, etc. Since Retinal blood vessels are vital for such diagnostics, the segmentation of retinal blood vessels is an important and active research area. This paper proposes an automated method for the identification of blood vessels in color images of the retina. For every image pixel, a feature vector is computed that utilize properties of scale and positioning selective Gabor filters. In this paper, we propose a Support Vector Machine based algorithm for retinal blood vessel classification by using chromaticity and image matting coefficients as features. In this paper, the proposed algorithm was tested on the standard benchmark retinal images from the DRIVE data set. Results were equated with available ground truth images and other approaches from literature and vessel segmentation were excellent in all cases.
Article Details
Unique Paper ID: 149101

Publication Volume & Issue: Volume 7, Issue 2

Page(s): 375 - 383
Article Preview & Download


Share This Article

Go To Issue



Call For Paper

Volume 7 Issue 3

Last Date 25 August 2020

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies