Full reference fusion-based image objective quality evaluation method

An evaluation method and objective quality technology, applied in the field of image processing, can solve the problem that the full reference measurement method is not enough to reflect the visual characteristics of the human eye, and achieve the effect of high consistency and high regression accuracy.

Inactive Publication Date: 2018-07-27
TIANJIN UNIV
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that a single full-reference measurement method is not enough to reflect the visual characteristics of human eyes in image quality evaluation, the present invention proposes a full-reference fusion image objective quality evaluation method, which can predict a quality score that is highly consistent with the subjective evaluation of human eyes

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
  • Full reference fusion-based image objective quality evaluation method
  • Full reference fusion-based image objective quality evaluation method
  • Full reference fusion-based image objective quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Attached below figure 1 The invention is further elaborated.

[0015] The first step is database selection.

[0016] The experimental material is selected from the LIVE Release 2 database, which contains 29 reference images, 5 distortion types JPEG2000, JPEG, White Noise, Gaussian Blur and Fast Fading Rayleigh, and each distortion type has images with different degrees of distortion. The specific information of the database is shown in Table 1.

[0017] Table 1 LIVE Release 2 database information

[0018]

[0019] The second step is feature extraction.

[0020] The present invention selects gradient similarity (Gradient SIMilarity index, GSIM), feature similarity with color information (Feature SIMilarity with Chrominance information, FSIM) C ), Gradient Magnitude Similarity Deviation (GMSD), Gradient Similarity based Metric (GSM), Internal Generative Mechanism (IGM), Multi-Scale Structural SIMilarity, MS-SSIM) 6 kinds of FR measurement methods, composed of FRme...

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 relates to a full reference fusion-based image objective quality evaluation method. The method comprises the steps of selecting a picture database as an input of model training, groupingpictures according to distortion types, and obtaining file names and tags of picture groups, wherein the pictures with different distortion degrees exist in each distortion type; performing feature extraction, selecting and using multiple full reference measurement algorithms to score the pictures in each distortion type, calculating the picture groups by the full reference measurement algorithmsto obtain eigenvectors, and forming a feature matrix by the obtained eigenvectors; performing data preprocessing, normalizing eigenvector scores corresponding to the distorted image tags and the distortion types to be in ranges (1,100) and (0,1), and performing transposition processing to meet SVM training needs; and performing feature training to obtain a quality evaluation model.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to the quality evaluation of plane images. Background technique [0002] With the development of information technology, people's demands for obtaining information through various display devices are gradually increasing. As a tool for information expression and communication, digital images have been widely used. However, in the actual process of image acquisition, analysis, transmission, processing and reconstruction, distortion will inevitably occur. Therefore, in order to ensure the quality of experience for end users, image quality evaluation plays an important role [1] . [0003] Image quality evaluation is divided into subjective evaluation methods and objective evaluation methods. Since humans are the ultimate recipients, the most reliable method is subjective evaluation, but the disadvantage is that it is time-consuming and labor-intensive, and it is difficult to apply in ...

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): G06T7/00
CPCG06T7/0002G06T2207/30168
Inventor 侯春萍李浩岳广辉
Owner TIANJIN 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