Open AccessArtery-Vein Detection using Neural Network in Retina Images
Author(s) -
K. Sonali Swaroop,
Sandeep Kumar,
A. Mary Sowjanya
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1042/1/012002
Subject(s) - computer science , artificial intelligence , benchmark (surveying) , computer vision , segmentation , fundus (uterus) , process (computing) , set (abstract data type) , image segmentation , task (project management) , artificial neural network , pattern recognition (psychology) , radiology , medicine , engineering , geodesy , systems engineering , programming language , geography , operating system
Retinal veins segmentation play a vital role in the life because of entire world moves toward the digital words. The paper presents an approach to identify the blood vessels from the optically affected areas of an eye. This method is proposed as the manual extraction of vessels from the fundus image is a very tedious task also it takes higher amount of time. Therefore, the paper mainly focuses on the developing an approach for vessel extraction. The methodology reportedly excels in terms of accuracy also being simple it finds many applications in image diagnosis for predicting various pathological diseases opathalmologically. It can create a new perspective in disease detection in a more accurate way. The input images are initially preprocessed; next the features are extracted from the images. The extracted images form the training set and the testing process is performed using the proposed methodology. Finally, the proposed work achieved 96.8% accuracy on benchmark datasets.