Objective stereo image quality assessment method based on perception feature set

Abstract

The invention discloses an objective stereo image quality assessment method based on a perception feature set. According to the method, the distortion degree of a stereo image is measured according to the distortion degree of a visual perception feature map, a saliency map, a gradient map and an airspace just noticeable distortion map which are related to viewpoint perception quality are extracted, a disparity map related to third dimension and quality is extracted, distortion degrees of four perception feature maps are taken as features of the stereo image to create the perception feature set, a complicated human vision system is simulated according to a random forest machine learning algorithm, and feature parameters are fused. The objective stereo image quality assessment method has the advantages that change conditions of visual quality under the condition that the stereo image is influenced by various image processing and compressing methods can be reflected objectively, assessment performance of the method is not influenced by the content of the stereo image and the type of distortion, and conformity with subjective perception of human eyes is achieved.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to an objective evaluation method for stereoscopic image quality based on a perceptual feature set. Background technique [0002] Stereo Image Quality Assessment (SIQA) is an important part of stereoscopic video technology. Stereoscopic images / videos will inevitably introduce noise or distortion during acquisition, storage, processing, and transmission, resulting in a decline in the quality of stereoscopic images / videos. Therefore, the evaluation of stereoscopic image / video quality is an important issue that needs to be studied and solved. . Stereoscopic image quality evaluation methods are generally divided into subjective and objective evaluation methods. Subjective evaluation methods are difficult to implement and apply due to their time-consuming, laborious, and costly shortcomings; while objective evaluation methods are integrated algorithms and models that can quickly an...

AI Technical Summary

Problems solved by technology

The second category: on the basis of the planar image quality evaluation method, adding disparity information to improve the evaluation model of the stereo image, such as Yang et al., who added the absolute difference map of the stereo image to evaluate the stereo image quality; and Benoit et al. The planar image quality evaluation method is combined with the evaluation of stereoscopic image quality; Hachicha et al. proposed a stereoscopic image quality evaluation method based on binocular just detectable distortion, and used binocular fusion competition to measure the change of stereoscopic effect. The results of eye fusion, binocular competition, and binocular suppression are very complex, so the measurement of stereoscopic perception is very difficult, which also leads to low consistency between these methods and subjective perception

The above three-dimensional image quality evaluation methods all obtain the global quality from the local quality, or use linear or nonlinear feature fusion methods to obtain the objective quality of the stereo image. However, the human visual system is an extremely complex system, and these evaluation methods cannot be better. Simulates the complex human visual system in an inaccurate way, resulting in low evaluation accuracy

Images