Non-reference image quality evaluating method based on wavelet and structural self-similarity analysis

Abstract

The invention discloses a non-reference image quality evaluating method based on wavelet and structural self-similarity analysis, which is used for image quality evaluation of grayscale images and belongs to the technical field of image processing. The method comprises the steps of: firstly, recombining an original image to be evaluated into a new image comprising 4<n>self-similarity sub-blocks; then, carrying out wavelet decomposition on the new image; computing a wavelet entropy; and finally evaluating quality according to a wavelet entropy value, wherein the smaller the wavelet entropy value is, the higher the quality of the images is and the better a visual effect is. Compared with other similar methods, in the method of the invention, a wavelet decomposition algorithm and the self-similarity of the images are combined for the first time; the entropy of a wavelet coefficient is computed for the first time; and a computing result (the wavelet entropy) is used for evaluating the quality of the images. Meanwhile, in the method, any reference image is not needed.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a non-reference image quality evaluation method based on wavelet and structural self-similarity analysis, which is used for quality evaluation of grayscale images and belongs to the field of image processing. Background technique [0002] The objective evaluation of image quality is a very important and difficult problem in digital image processing. Most of the traditional image quality evaluation methods belong to the full-reference evaluation method. Including the common mean-squared error MSE algorithm, signal-to-noise ratio evaluation method (signal-to-noise ratio SNR), and peak signal-to-noise ratio evaluation method (peak signal-to-noise ratio PSNR). These evaluation methods are widely used in image compression, fusion, forensics and other fields [Martin Vetterli S Grace Chang, Bin Yu. "Adaptive wavelet sharing for image denoising and compression", IEEE Transaction on ...

AI Technical Summary

Problems solved by technology

Although some new evaluation methods have emerged, most of them do not show superiority over MSE and PSNR methods.

[0003] Xie Zhengxiang, Liu Yuhong, and Hu Qin proposed a "no-reference image quality evaluation based on information entropy and contrast" in a Chinese invention patent application (application number 200810070170.1, application date 2008.8. Method", this method uses entropy and image grayscale to evaluate image quality without reference. Although the principle of entropy is used, it only considers the distribution characteristics of image grayscale in the global space, and does not consider the ability of human eyes to judge the quality of images according to the image quality. Factors for adaptive adjustment of features on the whole and in details

Images