In recent years, learning-based methods have been frequently exploited to tackle this problem, which correspond to promising calculation efficiency and performance, especially in image sharpening processing based on deep neural networks. Learning-based methods can be generally categorized as conventional methods and deep learning-based methods. This survey aims to review deep learning-based image super-resolution methods, Generative Adversarial Networks (GAN) based on internal network structure are used to improve the quality of our image. Recently, the deep learning methods have shown great advantages that the deep learning SR model directly establishes the end-to end relationship from LR and HR images using multi layer neural networks. Furthermore, this paper describes the applications of single-frame image super resolution in various practical fields. It will show the accuracy on the hardware kit through audino data interfaces to display the output in the Lcd. Experimental results shown the better performance of the system.