Convergence Neural Network based complete reference image quality evaluation

摘要

Embodiments generally relate to providing a system and method for evaluating the image quality of a distorted image for a reference image. In one embodiment, the system includes a convolutional neural network that accepts distorted images and reference images as inputs and provides metrics of image quality as outputs. In another embodiment, the method includes inputting a distorted image and a reference image to a convolutional neural network configured to process the distorted image and the reference image to provide a metric of image quality as an output.