A Quality Evaluation Method of Relocation Stereo Image Based on Structural Features

Abstract

The invention discloses a method for evaluating the quality of a relocated stereoscopic image based on structural features, which calculates the local information preservation feature of the relocated virtual viewpoint image, the forward information loss of the original virtual viewpoint image, and the reconstruction from the original virtual viewpoint image. The backward information loss of the virtual view point image is obtained, the spatial structure feature vector of the repositioned virtual view point image is obtained, and all the disparity images between the left and right view point images of the repositioned stereo image are calculated. The parallax amplitude features of the pixels belonging to the cross parallax area and the relative width features of all the pixels belonging to the occlusion area are obtained to obtain the depth structure feature vector, and finally the structure feature vector of the repositioned stereo image is obtained; The feature vector is trained to obtain the support vector regression training model; the advantage is that the correlation between the objective evaluation result and the subjective perception of the human eye is improved.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a structural feature-based repositioning stereoscopic image quality evaluation method. Background technique [0002] With the popularization of terminal display devices such as smartphones, tablet computers, and TVs with different resolutions and screen aspect ratios, when the resolution of the image or video to be displayed does not match the resolution of the screen, how can the Under the premise of not changing the user's viewing experience, changing the resolution of an image or video to adapt it to terminal display devices of different sizes is the problem of adaptive display. Current typical adaptive display methods include scaling, cropping, and warping. However, these adaptive display methods do not take full advantage of the size advantage of the terminal display device and reduce the user experience effect. Therefore, it is necessary to objectively evaluate the per...

AI Technical Summary

Problems solved by technology

However, the quality of stereoscopic images not only includes the image content itself, but also factors such as excessive binocular parallax, binocular asymmetry, and binocular accommodation and convergence conflicts will seriously affect the viewing comfort of stereoscopic images.

Therefore, compared with the planar relocation method, the stereo image relocation technology needs to consider more geometric distortion factors, which also greatly increases the complexity of the stereo image relocation technology.

Images