In many critical areas, notably medical imaging and satellite surveillance, high-resolution (HR) images are needed for comprehensive analysis, given that low-resolution (LR) images are devoid of important details. Admittedly, conventional image enhancement techniques are fraught with problems associated with slow processing times and low quality, precluding them for real-time use. Against this backdrop, this undertaking seeks to overcome such constraints by investigating Single Image Super-Resolution (SISR) with the use of Convolutional Neural Networks (CNNs), in particular the Enhanced Deep Super-Resolution (EDSR) model. Specifically, the goal of this endeavor is to enhance image resolution and quality by optimizing the EDSR model and assessing its performance on the DIV2K dataset, which was performed in real time through an intuitive web application. Remarkably, the assessment revealed a notable enhancement in image quality, made evident by improved Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) scores. As such, these revelations signify the practical importance of Single Image Super Resolution (SISR) in improving the quality of images for effective use in many critical domains.