A non-reference stereoscopic image quality evaluation method based on convolution neural network

A convolutional neural network, stereo image technology, applied in the field of image processing

Inactive Publication Date: 2019-01-18
ZHEJIANG UNIV
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a no-reference stereoscopic image quality evaluation method based on convolutional neural network for the deficiencies of existing image quality evaluation methods

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
  • A non-reference stereoscopic image quality evaluation method based on convolution neural network
  • A non-reference stereoscopic image quality evaluation method based on convolution neural network
  • A non-reference stereoscopic image quality evaluation method based on convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The method of the present invention will be further described below in conjunction with the accompanying drawings.

[0044] Such as figure 1 As shown, a no-reference stereo reference image quality evaluation method based on convolutional neural network, its specific implementation steps are as follows:

[0045] Step (1). Input the distorted image I dis and the reference image I ref , the distorted image I dis and the reference image I ref Each contains two views, left and right;

[0046] Step (2). Based on structural similarity (Structural Similarity Index, SSIM, Z.Wang, A.C.Bovik, H.R.Sheikh, and E.P.Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, no.4, pp.600-612, 2004) for parallax estimation, define the upper left corner of the image as the coordinate origin, and take the pixel point p in the left view 1 (x 1 ,y 1 ) as a benchmark, look for pixel point p on the right view...

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 invention discloses a non-reference stereoscopic image quality evaluation method based on a convolution neural network. Firstly, according to the stereoscopic perception characteristics of human visual system, the left and right views of stereoscopic image are fused into the middle view to simulate the process of stereoscopic perception of human eyes. Then the convolution neural network (CNN)is used as the feature extraction tool, the concept of transfer learning is used to adjust a convolution neural network to extract quality-related features from images adaptively, and the strong feature expression ability of neural network is utilized to avoid the incompleteness and high complexity in the process of manual modeling. Finally, the features extracted from the convolution neural network are sent to the support vector regression model, which is used to establish a mapping between the subjective scoring value and the features, so as to obtain the final quality evaluation score. Theimage quality objective evaluation score based on the method provided by the invention has high consistency with the subjective quality score provided by the database, and has good accuracy and robustness.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for evaluating the quality of a three-dimensional image without reference based on a convolutional neural network. Background technique [0002] With the rapid development of multimedia technology, human beings have gradually stepped into an era of high-definition and intelligent digital vision. The information carried by images is more intuitive and realistic than other forms of information, and it plays a very important role in the process of human information extraction and cognition establishment. Compared with planar (2D) images, stereoscopic (3D) images bring more realism and enhance the visual experience, and have attracted wide attention in many research fields and entertainment applications. In the process of image acquisition, storage, transmission, and processing, there are factors such as imperfect system imaging processing technology, n...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/55G06T7/49
CPCG06T7/0002G06T7/49G06T7/55G06T2207/20228G06T2207/30168
Inventor 丁勇李佳乐戴悦孙阳阳刘毅邓瑞喆
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap