SUPER_RESOLUTION_DL

Created a Super Resolution Convolutional Neura Network (SRCNN) model using Keras which is basically used to recover a high resolution image from a low resolution input.This network was published in the paper, "Image Super-Resolution Using Deep Convolutional Networks" by Chao Dong, et al. in 2014. The paper's link is: https://arxiv.org/abs/1501.00092. The SRCNN is a deep CNN model that learns end to end mapping of low resolution to high resolution images. Therefore we can improve the quality of low resoluton images whic is an extremely useful application in many sectors such as health, crime, etc. OpenCV is used for this project for processing our images. To evaluate the performance of the network we usethree image quality metrics:peak signal to noise ratio, mean squared error, structural similarity.