An Objective Evaluation Method of Stereo Image Quality Based on Perceptual Feature Set
A technology for objective quality evaluation and stereoscopic images, which is applied in the field of objective evaluation of stereoscopic image quality based on perceptual feature sets, and can solve the problems of difficult measurement of stereoscopic perception, low evaluation accuracy, and low consistency of subjective perception
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2017-05-24
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to an image quality evaluation method, in particular to an objective evaluation method of 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 in the collection, storage, processing and transmission, resulting in the degradation of stereoscopic image / video quality. 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 two categories: subjective and objective. The subjective evaluation method is not easy to realize and apply due to its shortcomings of time-consuming, laborious and high cost; while the objective evaluation method is an integrated algorithm and model, which can quickly and ...
Examples
Embodiment Construction
[0046] The present invention will be further described in detail below with reference to the embodiments of the accompanying drawings.
[0047] Human eyes have different degrees of sensitivity to distortion in stereo images, so the evaluation method of global quality obtained from local quality is less consistent with subjective perception, while perceptual feature maps are the shallow reflection of stereo images in the human nervous system. Image is the most intuitive feeling in the human eye. When the distortion of the stereoscopic image leads to the distortion of the perceptual feature map, the human eye will also be sensitive to detect these distortions. Therefore, the objective evaluation method of the stereoscopic image quality proposed by the present invention extracts four kinds of perceptual feature maps, It includes saliency map, gradient map, spatially perceptible distortion map and disparity map, and uses the degree of distortion as a characteristic parameter to for...