jit.6.4.13846 A Novel Approach for Image Super Resolution Problems with Convolution Neural Networks Chidadala Janardhan K.V. Ramanaiah K. Babulu Journal on Information Technology 2277-5250 6 4 15 22 10.26634/jit.6.4.13846 Super Resolution, Convolution Networks, Sparse Representation, Image Restoration, Interpolation The High Resolution Images (HRI) are more attractive in order to process the tasks like patient health monitoring, Machine inspection in industry, identify the missing objects location with the help of satellite images, missing number plate reorganization, criminal fingerprint identification, and many more. Images are degraded because of insufficient sensor resolution of the acquisition device, moving of object or camera and during transmission, processing and storing. Over the decades many researchers have proposed different approaches to solve these problems. The process of constructing High Resolution image from cluster of low resolution pictures or single low resolution image is named image super resolution. In this paper, the authors have evaluated various classes of super resolution algorithms, such as Iterative Back Projection (IBP), Sparse Representation (SR), and Convolution Neural Networks (CNN) with their performances. After evaluation Super Resolution with Deep Convolution networks can give best results over the state of the methods in terms of PSNR and quality of the image. This paper also gives some directions to future researchers to solve more ill posed problems. September - November 2017 Copyright © 2017 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=13846