No-reference screen image quality assessment method based on unsupervised feature learning

Abstract

The invention discloses a non-reference screen image quality evaluation method based on unsupervised feature learning, which first acquires normalized screen images of several undistorted screen images; then according to the normalized screen images, ZCA operation and Unsupervised clustering algorithm to obtain the dictionary codebook; then obtain the normalized screen image of the distorted screen image to be evaluated; then use the Gaussian kernel similarity weight method and the K-Nearest Neighbor method to process the normalized screen image to obtain Weight feature matrix; then according to the dictionary codebook and weight feature matrix, and use the LLC algorithm to obtain the LLC feature vector; finally use the support vector regression technology to test the LLC feature vector, and predict the objective quality of the distorted screen image to be evaluated Evaluation prediction value; the advantage is that it can fully take into account the impact of local information changes on visual quality, thereby improving the correlation between objective evaluation results and subjective perception.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a non-reference screen image quality evaluation method based on unsupervised feature learning. Background technique [0002] Image is an important way for human beings to obtain information. Image quality indicates the ability of image to provide information to people or equipment, and is directly related to the adequacy and accuracy of the information obtained. However, in the process of image acquisition, processing, transmission and storage, due to various factors, there will inevitably be degradation problems, which brings great difficulties to information acquisition or post-processing of images. Therefore, it is very important to establish an effective image quality evaluation mechanism. For example, it can be used for performance comparison and parameter selection of various algorithms in image denoising, image fusion and other processing processes; it can be used to g...

AI Technical Summary

Problems solved by technology

[0005] The existing general-purpose no-reference image quality evaluation methods are mainly aimed at general images, and there are relatively few studies on special images (such as screen images). Since screen images contain text, graphics, and images, etc., the general No-reference evaluation methods are more challenging

Images