In our thesis, we address the critical need for a rapid and accurate Covid-19 detection method amid the global pandemic. We explore various existing techniques such as PCR tests, antigen and antibody tests, chest CT scans, and chest X-rays, each with distinct levels of accuracy. Notably, we focus on the cost implications, pointing out the substantial expense of CT scans compared to X-rays. Our proposed solution leverages deep learning techniques, specifically investigating image enhancement methods like CLAHE, HEF, and UM, alongside the ESRGAN model. We aim to enhance the accuracy of Covid-19 detection using X-ray images. Our experimental studies, involving popular deep learning models (ResNet and VGG-16), demonstrate a significant improvement in accuracy through image enhancement techniques. This proposed methodology holds promise for the development of cost-effective and accurate Covid-19 detection methods, particularly suitable for resource-limited settings.