Relocation stereo image quality evaluation method based on structural features

Abstract

The invention discloses a relocation three-dimensional image quality evaluation method based on structural features, which comprises the following steps of: calculating local information retention features of a relocation virtual viewpoint image, forward information loss of an original virtual viewpoint image and backward information loss of a virtual viewpoint image reconstructed from the original virtual viewpoint image; obtaining a spatial structure characteristic vector of the relocated virtual viewpoint image; calculating parallax amplitude characteristics of all pixel points belonging to a matching region, a visual comfort region and a cross parallax region and relative width characteristics of all pixel points belonging to a shielding region in a parallax image between a left viewpoint image and a right viewpoint image of the repositioned stereo image to obtain a depth structure characteristic vector; and finally obtaining a structural feature vector of the relocated stereo image; then training all the structural feature vectors by using support vector regression to obtain a support vector regression training model; the method has the advantage that the correlation between an objective evaluation result and human eye subjective perception 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...

Images