No-reference image quality evaluation method based on adversarial generative network

Abstract

The invention discloses a no-reference image quality evaluation method based on an adversarial generative network. The method comprises the steps of firstly preprocessing an image to obtain a similargraph-SSIM _ MAP corresponding to a distortion graph, then training a neural network framework based on a densenet network, inputting the distortion graph into the trained network to obtain the similar graph of the distortion graph, and obtaining a corresponding quality score through the similar graph. Innovations are made for a generator and a loss function in a network. The method comprises thefollowing steps: firstly, in a generation network part, adopting a 60-layer densenet network framework; in the discrimination network part, adopting a simple classification network; and in the loss function part, adopting a mode of adding L1 norm loss to the cross entropy of a discriminator; and finally, iteratively training a relatively good generation network model, and generating a similar picture for an output picture, namely a distorted picture, through the network.

Description

technical field [0001] The invention belongs to the field of image processing, designs an image quality evaluation method, and relates to the application of a generation confrontation network in deep learning to image quality evaluation. Background technique [0002] Nowadays, with the rapid development of Internet technology and communication technology, digital images have become an important way of information transmission in people's daily life. According to statistics, since 2011, the total number of digital photos produced in the world has reached tens of billions, and this number is still increasing year by year. However, images are susceptible to different kinds of distortions during the process of acquisition, storage, compression, and transmission, resulting in reduced image quality. Therefore, how to evaluate image quality accurately and reliably has become an important research hotspot in current and future research. Usually, most images are viewed by people, s...

AI Technical Summary

Problems solved by technology

[0005] Most of the existing no-reference quality evaluation methods are evaluation methods with known subjective quality scores. Such methods usually require a large number of training sample images and corresponding subjective scores to train the quality prediction model. In contrast, subjective quality scores are unknown. There are still few reference-free evaluation methods and the performance of existing methods is still not comparable to methods with known subjective quality scores

Images