EXTRACT FEATURES AND CLASSIFICATION OF CHEST X-RAY IMAGES

Abstract

COVID-19 causes an epidemic of acute respiratory infections, with more than 90 million infections and more than 2 million deaths worldwide. The disease is transmitted through the respiratory tract, each day there are more than 300,000 new infections. In this study, we examine deep learning features on chest X-ray images and use traditional machine learning methods including k-Nearest-Neighbors (k-NN), Support Vector Machines (SVM), Logistic Regression for the problem of classifying X-ray images into three classes: COVID-19, PNEUMONIA, NORMAL. Evaluation results on a data set of 3423 chest X-ray images compiled from four datasets COVID-19 Radiography Database, Covid-19 Image Dataset, COVID-19 PatientsLungs X-Ray Images 10000, COVID19 High-quality images published in 2020, the detailed experimental results, analysis, and assessment will be the basis for the next researches.