ABSTRACT
SARS-CoV-2-virus, or COVID-19, is an infectious disease that makes people's lives turn inside out. The disease spread drastically worldwide, affecting the world's socioeconomic balance. Currently, most parts of the world rely on antigen tests or RT PCR tests for diagnosing patients with symptoms of Covid-19. However, in an outbreak where a large group of people gets the symptoms, it will be challenging to conduct the tests for all in a short period;therefore, finding alternates as a backup plan is essential. Many studies were conducted to simplify and automate disease identification using CXR images for that specific purpose. The proposed system aims to compare a ResNet-50 based Covid detection model with a deep CNN model to analyze the difference in terms of performance and efficiency of the models. Both models are trained and tested on the same dataset for better comparison. In this study, both CNN and ResNet-50 model achieved an accuracy of 96 percent, whereas ResNet-50 performed slightly better on the test dataset. © 2022 IEEE.