ABSTRACT
COVID-19 pandemic is triggering a massive epidemic in more than 180 countries worldwide, causing chaos in many people's health and lives. Identifying infected patients early enough and placing them under special treatment is one of the most critical steps in combating COVID-19. RT-PCR is a standard test process. The test procedure is typically conducted by air samples collected using a nasopharyngeal swab. However, using a nasal swab or sputum extract is not always possible. Due to the shortage of testing kits, virus mutations, and a longer time to detect. In addition to laboratory tests, chest scans can help diagnose COVID-19 in people who have severe clinical concerns. So, classification through X-ray images could be beneficial. This experiment aims to analyze the X-Ray images as abnormal or not. The intention is to train a convolution neural network(CNN) to classify the image using different architectures such as Xception, Resnet-50, DenseNet-121, VGG-16. Test the Performance metrics for each model and train further based on the insight gained. The following is an experimental study where we repeatedly train better models based on the insights gained from the previous model. The models tested on test data, and most of the results achieved a sensitivity rate of 98 percent (± 2 %), With a specificity rate of around 98 percent. While the achieved results are auspicious, additional research in a broader collection of COVID-19 chest X-ray pictures is needed to estimate accuracy rates accurately. © 2021 IEEE.