Stereo image objective quality evaluation algorithm based on GSSIM

Abstract

The invention belongs to the image processing field and relates to a stereo image quality evaluation method based on GSSIM. The method includes the steps: (1) for left image and right image, gradient structure similarity values are respectively solved, the average of the two values is solved, so as to obtain stereo image quality evaluation value QE; (2) the following method is adopted to carrying out image stereoscopic perception objective evaluation: absolute difference image of the original image and processed image is calculated, Mu1 and Mu2 of the absolute difference image are solved; Sobel operator is used for solving the gradient amplitude image of the absolute difference image; filtering is carried out on the absolute difference image of the original image, and original image binocular parallax distribution situation is calculated; Dl(x, y), Dcg(x, y) and Dsg(x, y) values at binocular parallax position are solved; DSSIM value at the binocular parallax position is calculated; and image gradient structure similarity namely image stereoscopic perception objective evaluation value DE is calculated. The invention can be well applied to stereo image quality evaluation, and correlation of objective evaluation result and subjective evaluation result is strong.

Description

technical field [0001] The invention belongs to the field of image processing and relates to an objective quality evaluation algorithm of a stereoscopic image. Background technique [0002] The quality evaluation of stereoscopic images is a very difficult task. The existing objective quality evaluation algorithms for planar images can only evaluate the relationship between the image quality before encoding and after decoding for the same viewpoint. There is a high correlation of human standard parallax in stereoscopic images between adjacent viewpoints. If the image quality of two adjacent viewpoints is relatively high, the parallax components between viewpoints are reduced or even reversed, and the stereoscopic effect that human eyes can enjoy will be reduced. Therefore, the existing planar image objective quality assessment algorithm cannot replace the stereoscopic image objective quality assessment algorithm. If a kind of compression coding causes serious loss of stereos...

AI Technical Summary

Problems solved by technology

[0002] The quality evaluation of stereoscopic images is a very difficult task. The existing objective quality evaluation algorithms for planar images can only evaluate the relationship between the image quality of the same viewpoint before encoding and after decoding.

There is a high correlation of human standard parallax in stereoscopic images between adjacent viewpoints. If the image quality of two adjacent viewpoints is relatively high, the parallax compon

Images