In this paper we study and represent various techniques of image super resolution (SR), it is alsocalled as super resolution reconstruction. Super resolution reconstruction produces high resolution imagefrom sequence of low resolution images. The main aim of super resolution is to improve visual quality ofavailable low resolution image. Also existing Low Resolution (LR) imaging can be utilized with help of superresolution reconstruction. This paper focuses on reconstruction based and learning based super resolutionmethods. We have represented various existing super resolution techniques, advantages and disadvantages ofthose techniques, recent work and recent methods of super resolution reconstruction method. Finally wehave presented challenge issues and future research directions for super resolution.