A Survey on Fast Super Resoluted Image using Convolution Network

Aim of Super resolution is to generate high-resolution image from single or multiple low resolution of the same picture or image. With one single low resolution image it's very challenging to produce high-resolution image because a single low-resolution image contain the less information. Due to the ability of preserving edges, kind of method called Total variation based method was proposed as regularization function for some inverse problems. Novel super resolution method proposed which based on Total Variation regularization and total variation up sampling with Gaussian noise which provide better resolution image with preserving only texture components. But still it takes the more processing time due to the calculation of total variation in the input Image. To overcome problem of existing work, Novel approach of neural network which is consists of three layers namely convolution layer, max-pooling layer and reconstruction layer. This approach will try to reduce the processing time as well as increasing the PSNR ratio.