Stereo image visual conform evaluation method based on multi-scale dictionary

Abstract

The invention discloses a stereo image visual conform evaluation method based on a multi-scale dictionary. The stereo image visual conform evaluation method comprises the following steps: in a training phase, selecting multiple stereo images of different comfort levels to constitute an initial training image set, calculating a parallax statistical feature vector and a neural response feature vector of each stereo image in the initial training image set to obtain the multi-scale dictionary and a corresponding multi-scale quality table, in this way, a relation model between the feature vector and the quality is established, and thus the quality of the image can be directly predicted by simple mapping; and in a testing phase, calculating the feature vector of a tested stereo image, predicting conform evaluation predictive values corresponding to different comfort levels according to the multi-scale dictionary and the multi-scale quality table, and obtaining final objective visual conform evaluation predictive values in combination with the conform evaluation predictive values corresponding to the different comfort levels. Good consistency is kept with subjective evaluation values, namely the correlation with subjective perception is high.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a multi-scale dictionary-based visual comfort evaluation method for stereoscopic images. Background technique [0002] With the rapid development of stereoscopic video display technology and high-quality stereoscopic video content acquisition technology, the quality of experience (QoE, quality of experience) of stereoscopic video is an important issue in the design of stereoscopic video systems, and visual comfort (VC, visual comfort) is an important factor affecting the visual experience quality of stereoscopic video. At present, research on the quality evaluation of stereoscopic video / image mainly considers the influence of content distortion on image quality, but seldom considers the influence of factors such as visual comfort. Therefore, in order to improve the visual experience quality of viewers, it is very important to study the objective evaluation model of visual co...

AI Technical Summary

Problems solved by technology

[0003] The traditional stereoscopic image visual comfort evaluation method is mainly based on machine learning, which requires a large amount of sample data to establish a regression model between the stereoscopic image visual comfort features and subjective evaluation values. However, the acquisition of subjective evaluation values ​​requires complex Subjective experiments, so time-consuming, not suitable for practical image processing applications

Images