SWS Academic Research eLibraryEarth & Planetary Sciences

Scholarly record

RETINAL VASCULAR SYSTEM EDGE DETECTION BASED ON WAVELET IMAGE FUSION AND FIRST ORDER DERIVATIVE ALGORITHMS

Cristian-Dragoș Obreja

First published: 2019-12-05https://doi.org/10.5593/sgem2019v/6.3/s08.025View metrics

Abstract

A vital role in detecting eye disorders is played by the analysis of the human retina using medical imaging methods. The main objective of this study is to improve the detection of retinal blood vessels by ameliorating the overall quality of non-uniform illumination conditions, removing image artifacts, connecting the broken vessels, and generating accurate segmented retinal vascular systems. A three-stage edge detection framework is proposed. First, image denoising, contrast enhancement, stretched decorrelation and image sharpening are performed. Then, edge detection operators to extract retinal vascular trees are adopted. Their output images are fused in pairs of two using a wavelet-based method with the objective to improve the accuracy of the extracted retinal vascular structure and connect discontinuous vessels. The performance of the fusion algorithm is assessed by comparing the blood vessel diameter values over the fused, first order derivative operators generated and ground truth images. The error rate and a structural similarity metric are calculated and are regarded as a performance analysis tool. The experimental results showed that the wavelet based fusion method was feasible and effective for an accurate edge detection process.

Publication Impact Profile

PlumX
  • Captures
  • Mendeley - Readers: 2
PLUMX see details

Publication details

Title
RETINAL VASCULAR SYSTEM EDGE DETECTION BASED ON WAVELET IMAGE FUSION AND FIRST ORDER DERIVATIVE ALGORITHMS
Authors
Cristian-Dragoș Obreja
Proceedings
SGEM International Multidisciplinary Scientific GeoConference EXPO Proceedings; 19th SGEM International Multidisciplinary Scientific GeoConference EXPO Proceedings19th, Nano, Bio, Green and Space: Technologies for Sustainable Future
Publisher
STEF92 Technology
Year
2019
Pages
189-196
SWS Citekey
Obreja20198189196
ISSN
1314-2704
ISBN
978-619-7408-99-7
Language
en
Publication type
Conference Paper
Keywords
wavelet-based fusionedge detection operatorsstructural similarity metric
References0
0references registered for this publication

Structured references will appear here after the reference import pass. The count is preserved now so the scholarly record is not incomplete.

View or Download full articleAccess options
Full paper accessChoose SWS login, librarian support, or instant article download.

SWS access login

Login as SWS Scientific Committee

Authors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.

For librarian assistance: [email protected]

Purchase Instant Access

48-hour online accessComing soon
Online-only accessComing soon
Download the full article in PDF formatEUR 35
  • Article can be downloaded after successful payment.
  • Article may be used according to SWS library access terms.
  • Article cannot be redistributed.
Get full paper

Back to publication list