A Deep Neural Architecture for Image Super Resolution

A machine learning model using a deep convolutional neural network architecture has been proposed in this paper. The model takes an LR image and generates the HR image by performing both upscaling and enhancement within itself. Such a network architecture has not been attempted before with this intention. The output of the network is analyzed and the results have been compared with the standard works in this area. The results seem to be distinctive concluding that the proposed architecture is better than the other methods in this area.