The coronavirus disease 2019 is a new contagious illness affecting the lungs and upper respiratory tract. It has various complications that can affect the quality of life. One of the most common factors that can be used to diagnose this illness is chest computed radiography. According to studies, deep learning can identify COVID-19 using chest radiography results. We created a CNN network to find COVID-19 in patients with Pneumonia and normal controls after a full chest X-ray. For the testing and training of the VGG16 model, we focused on its deep features. The study's results revealed that the VGG16 model had the highest accuracy score, at 70.0021%.