Non-reference stereo image quality assessment method based on deep neutral network

A deep neural network and stereoscopic image technology, applied in the field of no-reference stereoscopic image quality evaluation based on deep neural network, can solve the problem of low performance and achieve the effect of predicting the perceived quality

Active Publication Date: 2018-08-10
UNIV OF SCI & TECH OF CHINA
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, the aforementioned paper [5] and the no-reference convolutional neural network (NR-CNN) approach [6] have low performance

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
  • Non-reference stereo image quality assessment method based on deep neutral network
  • Non-reference stereo image quality assessment method based on deep neutral network
  • Non-reference stereo image quality assessment method based on deep neutral network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0023] Embodiments of the present invention provide a no-reference stereoscopic image quality evaluation method based on a deep neural network, such as figure 1 As shown, it mainly includes the following steps:

[0024] Step 1. Divide the left and right view images constituting all the distorted stereo images into non-overlapping distorted image blocks, and obtain several left and right view distorted image block pairs.

[0025] In the embodiment ...

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 stereo image quality assessment method based on a deep neutral network. Through the method disclosed by the invention, a left vision distortion image block anda right vision distortion image block are simultaneously input into a double-flow deep neutral network structure by considering an interaction principle of integration between the left vision and theright vision and parallax information in a multilayer structure of an eye vision system and using a non-reference 3D stereo image quality assessment algorithm based on the deep neutral network in end-to-end double-flow interaction, judgment feature extraction and regression learning are combined as an end-to-end optimization process, thereby achieving an aim of effectively predicting sensing quality of the distortion stereo image.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a method for evaluating the quality of stereoscopic images without reference based on a deep neural network. Background technique [0002] With the rapid popularization and development of 3D multimedia technology including 3D movies, 3D stereoscopic images have gradually entered people's daily life. Watching 3D stereoscopic images can produce an immersive visual experience that 2D images lack. At the same time, due to this additional depth perception and the asymmetric distortion between the left and right view images, it is more challenging to evaluate the quality of 3D stereoscopic images, that is, it is necessary to consider more complex binocular visual mechanism. [0003] The early full-reference 3D stereoscopic image quality assessment algorithm originated from the 2D image quality assessment method, such as the article [1] (A.Benoit, P.Le Callet, P.Campisi, and R.Co...

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): H04N17/00H04N13/106G06T7/00
CPCG06T7/0002G06T2207/10012G06T2207/20021G06T2207/20081G06T2207/20084G06T2207/30168H04N17/00H04N2013/0074
Inventor 陈志波周玮李卫平
Owner UNIV OF SCI & TECH OF CHINA
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