Non-reference screen content image quality evaluation method based on multiple scales

Abstract

The invention relates to a non-reference screen content image quality evaluation method based on multiple scales. The method comprises the following steps: S1, converting a distorted image from an RGBcolor space to an LMN color space, amplifying an L component by using a bicubic algorithm, and extracting edge features of the distorted image by using an imaginary part of a Gabor filter; s2, amplifying the grey-scale map of the distorted image by using a bicubic algorithm, and extracting the structural features of the distorted image by using a Scharr filter and a local binary pattern; s3, extracting brightness features of the distorted image by using a local normalization algorithm; s4, taking the obtained three features as training data, and training an image quality evaluation model by utilizing random forest regression; and S5, according to the steps S1-S3, obtaining edge features, structure features and brightness features of the to-be-detected image, and predicting the quality score of the to-be-detected image by using the trained image quality evaluation model. According to the invention, the reference-screen-free content image quality evaluation performance can be significantly improved.

Description

technical field [0001] The invention relates to the field of image and video processing and computer vision, and specifically relates to a multi-scale-based non-reference screen content image quality evaluation method. Background technique [0002] With the rapid development of mobile devices and multimedia applications, screen content images are increasingly appearing in multi-client communication systems, such as online news, e-magazines, e-commerce, cloud games, and cloud computing, etc. During the processing of images, such as transmission, compression, and redirection, due to technical reasons, this will introduce distortion and reduce image quality, thereby affecting user experience. Image quality assessment can be used to test the performance of image processing related technologies, and can also guide its development. Therefore, a good image quality assessment method for screen content is very important. [0003] In recent years, scholars have proposed many effectiv...

AI Technical Summary

Problems solved by technology

In the above two works, segmentation is required to distinguish text and image regions, which has two obvious disadvantages. On the one hand, this obviously increases the computational complexity. On the other hand, due to incorrect segmentation, this incorrect segmentation will Areas of graphics are mistaken for areas of text, which can seriously reduce the accuracy of algorithms in assessing image quality

Shao et al. proposed a no-reference image quality assessment method by using a sparse representation framework, which requires four full-reference methods to generate labels for images, but these four methods are relatively poor in predicting the image quality of screen content. , resulting in poor performance of the entire algorithm

[0004]Most of the methods currently proposed are full-reference methods. However, full-reference methods require all original image information, but these information are often not available in practical applications. There are still relatively few reference-free methods proposed so far, and these reference-free methods are relatively ineffective and cannot produce high consistency with subjective perception

Images