A method for objective evaluation of multi-distortion stereoscopic image quality

Abstract

The invention discloses a multi-distortion stereo image quality objective evaluation method, and the method comprises two stages: a training stage and a testing stage. The training stage comprises the steps: obtaining a JPEG distortion stereo image, a Gaussian blur distortion stereo image and a Gaussian white noise distortion stereo image of a non-distortion stereo image, respectively constructing three training image sets, and respectively obtaining an image feature dictionary table and an image quality dictionary table, which are different in distortion type, through combined dictionary training, wherein the JPEG distortion stereo image, the Gaussian blur distortion stereo image and the Gaussian white noise distortion stereo image are different in distortion intensity. The testing stage comprises the steps: obtaining the sparse coefficient matrix of each sub-block in a testing stereo image through optimization according to the image feature dictionary tables which are obtained at the training stage and are different in distortion type; calculating an image quality objective evaluation prediction value for testing the stereo image through the sparse coefficient matrixes and the image feature dictionary tables which are obtained at the training stage and are different in distortion type, wherein the image quality objective evaluation prediction value is consistent with a subjective evaluation value better.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to an objective evaluation method of multi-distortion stereoscopic image quality. Background technique [0002] With the rapid development of image coding and display technologies, the research on image quality evaluation has become a very important link. The objective of the research on the objective evaluation method of image quality is to be consistent with the subjective evaluation results as much as possible, so as to get rid of the time-consuming and boring subjective evaluation method of image quality, which can automatically evaluate the image quality by computer. According to the degree of reference and dependence on the original image, objective image quality evaluation methods can be divided into three categories: full reference (FR) image quality evaluation methods, partial reference (Reduced Reference, RR) image quality evaluation methods and no reference ( No Refe...

AI Technical Summary

Problems solved by technology

At present, the existing method is to predict the evaluation model through machine learning, but its computational complexity is high, and the training model needs to predict the subjective evaluation value of each evaluation image, which is not suitable for practical applications and has certain limitations.

Especially for the multi-distortion image quality evaluation problem, the existing single-distortion image quality evaluation methods cannot be directly applied. Therefore, how to construct a dictionary that can reflect the characteristics of multi-distortion images, how to construct a dictionary that can reflect the quality of multi-distortion images, How to establish a relationship between the dictionary that reflects the characteristics of multi-distortion images and the dictionary that reflects the quality of multi-distortion images, as well as between different types of distortion, are all technical problems that need to be solved in the research of non-reference multi-distortion image quality evaluation.

Images