Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Light field image quality identification method based on 3D-DOG features

A 3D-DOG and light field image technology, applied in the field of image processing, can solve problems such as not considering the special structure of light field images and not applicable to light field image quality evaluation, and achieve good light field image quality evaluation performance and high recognition Accuracy and Sensitivity and Effects of Robustness

Inactive Publication Date: 2021-06-22
HUAQIAO UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the existing quality evaluation methods are designed for traditional two-dimensional images, and do not take into account the special structure of light field images, and are not suitable for quality evaluation of light field images.

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
  • Light field image quality identification method based on 3D-DOG features
  • Light field image quality identification method based on 3D-DOG features
  • Light field image quality identification method based on 3D-DOG features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] see figure 1 As shown, a light field image quality recognition method based on 3D-DOG features, the specific steps are as follows:

[0034] S101: input the reference light field image L r and the distorted light field image L d Converted to the reference light field sequence V r and the distorted light field sequence V d ,details as follows:

[0035] Input reference light field image L r ={L r,1 , L r,2 ,...,L r,n} and the distorted light field image L d ={L d,1 , L d,2 ,...,L d,n}, where n represents the number of a group of sub-aperture images, select the sub-aperture images whose subscripts are singular one by one to form a light field image sequence according to the order of subscripts from small to large, and obtain the reference light field sequence V r and the distorted light field sequence V d .

[0036] S102: using the 3D-DOG filter to extract the reference light field sequence V respectively r and the distorted light field sequence V d The refe...

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 light field image quality identification method based on 3D-DOG features. The method comprises the following steps: converting an input reference and distortion light field image into a reference and distortion light field sequence; respectively extracting 3D-DOG features of the reference light field sequence and the distorted light field sequence by using a 3D-DOG filter; calculating the similarity of the reference light field sequence and the distortion light field sequence based on 3D-DOG features; and using a 3D-DOG feature pooling strategy to calculate a light field image quality score. According to the invention, the sensitivity of a human vision system to two-dimensional edge information and a three-dimensional geometric structure is fully considered, the scene edge information and the structure change of the light field image are effectively described by adopting the 3D-DOG features, and the invention has relatively good light field image quality evaluation performance.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for identifying the quality of light field images based on 3D-DOG features. Background technique [0002] With the rapid development of multimedia and imaging technology, light field image as a new type of media has attracted the attention of academia and industry, and has been widely used in the fields of computer vision and computer graphics, such as multi-view imaging, 3D reconstruction, and depth estimation. , virtual reality and augmented reality, etc. Different from traditional two-dimensional imaging, light field imaging can capture the position, direction and intensity information of any point in space. Therefore, the light field image has a specific 4-dimensional structure, which can better reflect the spatial and structural information of the real scene. [0003] Light field images inevitably produce various distortions in image acquisition, compression, trans...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/40G06V10/462G06F18/22
Inventor 曾焕强黄海靓侯军辉王勇涛曹九稳蔡灿辉
Owner HUAQIAO UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com