A comparative study of different feature extraction techniques for identifying COVID-19 patients using chest X-rays images

Abstract

The coronavirus (COVID-19) outbreak has been labeled as a pandemic with no assured vaccine and drug till now. Many medical trials are going on for finding treatment against this disease and some have achieved success but reaching out to all stakeholders is strenuous. A quick and proper identification through testing of a COVID-19 patient is equally important to prevent the spread of the virus to other healthy patients. Thus, a comparative study of different feature extraction techniques for identifying COVID-19 patients using chest X-rays images is done in this work. The combination of local binary patterns features extraction technique and gradient boosting classifier performs the best with 94.453% accuracy as compared to other approaches. So, this work will be of great help in the screening of COVID-19 and also contribute to the healthcare system to fight against it.