Coronavirus disease (COVID-19) is an infectious disease caused by the Severe Acute Respiratory Syndrome corona virus 2 (SARS-CoV-2) viruses. With a motive to detect and diagnose onset of COVID-19 diseases caused due to SARS-CoV-2 chest radiographs (X-rays) combined with deep convolutional networks (CNN) methods are being used. One of the critical factors behind the rapid spread of COVID-19 pandemic is a lengthy clinical testing time. The imaging tool, such as Chest X-ray (CXR), can speed up the identification process. But, there will be issues regarding accuracy, imbalanced datasets and their performance. To deliberate these issues various networks such as Dense Net, Resnet 101, Inception Net, Resnet 50, VGG16, and VGG 19 have proposed. Results are obtained in terms of precision, FSCORE, Accuracy and Recall using the datasets .Methods such as VGG16 and dense net provide 99.8% accuracy on the dataset, which means that these methods more accurately identify COVID-19 patients. A pilot test of VGG16 models on a multi-class dataset is being presented, showing promising results by achieving 91% accuracy in detecting COVID-19 and normal patients. In addition to that, the paper establishes the models (Resnet 101, Resnet 50, and Inception net) having poor performance having accuracy up to 78%. Still, model like VGG19 demonstrates an accuracy of 93% on both datasets, which postulates the effectiveness of our proposed methods, ultimately presenting an equitable and accessible alternative to identify patients with COVID-19.