A Holistic Approach to Identification of Covid-19 Patients from Chest X-Ray Images utilizing Transfer Based Learning

Novel coronavirus likewise called COVID-19 began in Wuhan, China in December 2019 and has now outspread over the world. Around 8 millions of individuals previously got influenced by novel coronavirus and it causes at any rate 500,000 deaths. There are just about 90,000 individuals contaminated by COVID-19 in Bangladesh too. As it is an exceptionally new pandemic infection, its diagnosis is challenging for the medical community. In regular cases, it is hard for lower incoming countries to test cases easily. RT-PCR test is the most generally utilized analysis framework for COVID-19 patient detection. However, by utilizing X-ray image based programmed recognition can diminish the expense and testing time. So according to handling this test, it is important to program and effective recognition to forestall transmission to others. In this paper, we attempt to distinguish COVID-19 patients by chest X-ray images. We execute different pre-trained deep neural system models, for example, Sequential, DenseNet121, ResNet152 and EfficientNetB4 to assess the most productive outcome. And aims to utilize transfer-based learning. We assess this outcome by AUC, where EfficientNetB4 has 0.997 AUC, ResNet50 has 0.967 AUC, DenseNet121 has 0.874 AUC and the Sequential model has 0.762 AUC individually. And EfficientNetB4 has achieved 98.86% accuracy.