Covid-19 is an abruptly transmitting disease which started from Wuhan, China that not only infects humans but also animals. It has affected approximately 82.1 M people worldwide to date, according to statistics. People's day by day lives, their wellbeing and the economy of the nation are influenced by this destructive viral infection. It is a typical irresistible sickness thus far, and not a solitary nation could set up a fruitful antibody for it. Contaminated patients with Coronavirus have demonstrated that these kinds of patients are generally tainted with lung disease upon contact with the illness. The Gold Standard for coronavirus is Reverse Transcription-Polymerase Chain Reaction controls for COVID-19 diagnosis (RT-PCR). Nevertheless, the RT-PCR test facility is sluggish, rendering early detection of the disease difficult. More effective and readily available imaging methods for diagnosing lung-related conditions are chest X-ray (i.e., radiography) and chest CT scan. However, in comparison to chest CT scans, significantly chest X-ray is a lower cost procedure. In addition, we demonstrate in this study how convolutional neural network (CNN) can be useful for using chest X-ray images to detect Covid-19. In addition, we took the pre-analyzed view of CNN models and compared their performance after cleaning the images and applying data augmentation to Covid-19 affected chest X-ray scans of patients along with healthy patients. We trained it on 907 samples to evaluate the output of the model and tested it on 101 samples. The focus of this research is on the potential methods for classifying infected patients with COVID19 and not claiming any medical precision.