Unlock instant, AI-driven research and patent intelligence for your innovation.

No-reference Stereo Image Quality Objective Evaluation Method Based on Spatial Features

A technology for objective quality evaluation and airspace characteristics, which is applied in the field of image processing to achieve the effect of high consistency and accurate reflection

Active Publication Date: 2019-06-14
TIANJIN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In addition, in view of the fact that the existing stereoscopic image quality assessment method requires the original reference image as the evaluation basis, it has great limitations, so the no-reference (that is, does not require the original reference image as the evaluation basis) stereoscopic image quality assessment method should be applied born

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • No-reference Stereo Image Quality Objective Evaluation Method Based on Spatial Features
  • No-reference Stereo Image Quality Objective Evaluation Method Based on Spatial Features
  • No-reference Stereo Image Quality Objective Evaluation Method Based on Spatial Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] No-reference stereo image quality objective evaluation method based on spatial features, each distorted stereo image pair is composed of a left image and a right image, and the distorted image pair is (t l ,t r ), including the following steps:

[0021] Step 1: Simulate the characteristics of human vision, for distorted image pairs (t l ,t r ) of the left and right images are subjected to two-dimensional Gabor filtering to obtain the corresponding energy responses, and then convolution and processing are performed, and the weighting factors of the left and right images are obtained after normalization operations: W L (x,y) and W R ((x+d), y), where (x, y) is the pixel coordinates, (x+d) represents the parallax compensation, and d represents the abscissa difference of the pixel point for parallax compensation on the right image; the calculation method is as follows

[0022] (1) The two-dimensional Gabor filter is:

[0023]

[0024] where G(x,y,σ x ,σ y ,ζ x ,ζ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a spatial feature-based non-reference three-dimensional image quality objective assessment method. The method includes the following steps: human visual characteristics are simulated, and two-dimensional Gabor filtering is performed on the left image and right image of a distorted image pair, so that the weighting factors of the left image and right image can be obtained; weighting operation is performed on the distorted image pair, and normalization processing is performed, and a visual perception image V(^)(x,y) of the distorted image pair is obtained, and blocking processing is performed on the visual perception image V(^)(x,y); the characteristic parameter of each image block is calculated; the size of the image is scaled to half of the original size of the image, the characteristic parameter of each image block of the scaled image is obtained, so that the spatial features of the visual perception image V(^)(x,y) can be formed; and the mean nud and a variance matrix Sigmad of the features are calculated; the multivariate Gaussian model of an undistorted reference image pair is trained, so that a mean nu and a variance matrix Sigma are obtained and are adopted as standard models; distances between nud and the standard model nu as well as between Sigmad and the standard model Sigma are calculated, namely, the objective prediction values of the quality of the three-dimensional image pair are obtained. According to the method of the invention, a two-viewpoint characteristic is fully considered.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a method for objectively evaluating the quality of stereoscopic images without reference based on spatial characteristics. Background technique [0002] In recent years, 3D technology has gradually become popular and entered the public life, bringing better visual experience and sense of presence to the audience, but at the same time, it also puts forward higher requirements for the quality of stereoscopic images. Since inappropriate processing of stereoscopic images may cause visual fatigue and discomfort to viewers, it is very necessary to propose a unified, objective and effective stereoscopic image quality evaluation method to accurately predict the quality of stereoscopic images. [0003] The existing stereoscopic image quality evaluation methods mainly include evaluation methods based on planar image quality parameters and evaluation methods based on the basic characteristics ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/10012G06T2207/20024G06T2207/20081G06T2207/30168
Inventor 杨嘉琛林彦聪姜斌汪亚芳沈教勋
Owner TIANJIN UNIV