Classification of COVID-19 using Chest X-ray Images with Deep Learning Techniques-CNN & ResNet-18

Abstract

To classify the covid-19 images as infectious or normal, it has been evident that the chest X-ray is a powerful tool to diagnose due to its crucial characteristics of convenience, inexpensiveness and rapid pace. The work aims to determine covid-19 in the infected patients by training models with the dataset using convolutional neural networks (CNN) and ResNet-18 and to draw comparisons in their performances respectively. To handle the dataset by applying various operations to simplify and to make it ready for training, validation and testing procedures of both the algorithms involved. The accuracies obtained on testing CNN and RESNET-18 models are 96.07% and 96.67% respectively. Hence the objective of the work is achieved and the results are obtained by implementing covid-19 classification using chest x-ray images with CNN and resnet-18 models.