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

Color image quality evaluation method based on joint entropy

A color image and evaluation method technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as quality distortion and degradation, achieve good evaluation performance, and quickly change pixel types

Active Publication Date: 2021-03-05
TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention provides a color image quality evaluation method based on joint entropy to solve the problem of quality distortion and degradation of digital images caused by image processing such as transmission, storage, compression, and editing

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
  • Color image quality evaluation method based on joint entropy
  • Color image quality evaluation method based on joint entropy
  • Color image quality evaluation method based on joint entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] In this embodiment, a standard image in the CSIQ (Categorical subjective image quality) database and two corresponding distorted images with different degrees of distortion are selected as the input of the present invention to describe the color image quality evaluation method described in the present invention. ; The CSIQ database contains 30 standard images and 866 distorted images. The distortion types of the distorted images include JPEG compression, JPEG2000 compression, overall contrast reduction, additive Gaussian pink noise, additive Gaussian white noise and Gaussian Fuzzy; the CSIQ database provides the average human perception error (DMOS) value of the distorted image. The value range of DMOS is [0, 1]. The larger the DMOS, the lower the image quality, and the worse the human perception effect .

[0036] image 3 It is the selected standard image, the file name is src_imgs1600; Figure 4 It is an additive white Gaussian noise distorted image with less distor...

Embodiment 2

[0040] In this embodiment, a standard image in the CSIQ database and two corresponding distorted images with different degrees of distortion are selected as the input of the present invention to describe the color image quality evaluation method of the present invention. The file name of the standard image is src_imgs1600; the selected distorted images are two distorted images compressed by JPEG2000 with different compression ratios, the file names are 1600.jpeg2000.1 and 1600.jpeg2000.3, and the DMOSs are 0.012 and 0.364 respectively , the image quality of the former is better than that of the latter; human eyes can hardly feel the difference between the JPEG2000 compression distortion image with the file name 1600.jpeg2000.1 and the standard image, while the JPEG2000 compression distortion image with the file name 1600.jpeg2000.3 The boundary between the flagpole tree and the sky in the image has blurred and blurred compressed edges.

[0041] With the image of file name src_...

Embodiment 3

[0044] In this embodiment, a standard image in the CSIQ database and two corresponding distorted images with different degrees of distortion are selected as the input of the present invention to describe the color image quality evaluation method of the present invention. The file name of the standard image is src_imgs1600; the selected distorted image is two JPEG-compressed distorted images with different compression ratios, and their file names are 1600.jpeg.1 and 1600.jpeg.3 respectively. Good; the difference between the JPEG-aliased image with the filename 1600.jpeg.1 and the standard image is barely perceptible to the human eye, while the boundary portion of the content inside the JPEG-aliased image with the filename 1600.jpeg.3 is There is blurring.

[0045] With the distorted image of file name src_imgs1600 and 1600.jpeg.1 as the input of the present invention, the image of file name src_imgs1600 is the standard image I of the step 1 of technical scheme of the present in...

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 provides a color image quality evaluation method based on joint entropy, and belongs to the technical field of digital image quality objective evaluation, machine vision and artificial intelligence. The joint entropy in statistics is used for measuring the quality difference between a distorted image and a standard image, the image quality evaluation method based on the special jointentropy is provided, and the problem of quality distortion degradation brought to a digital image when the image is transmitted, stored, compressed, edited and the like is solved. The obtained imagedistortion evaluation data can objectively describe and evaluate the distortion degradation degree of the image, and is consistent with human eye perception characteristics. According to the evaluation method, objective evaluation can be carried out on distorted images such as noise, blurring, JPEG compression and JPEG2000 compression, especially low-degree distorted images; an evaluation result conforms to human eye perception, and the method has good evaluation performance, can be used in the fields of image fusion, image analysis, intelligent detection and the like, and has good applicationpotential and value.

Description

technical field [0001] The invention relates to the technical fields of objective evaluation of digital image quality, machine vision, artificial intelligence and the like, in particular to a color image quality evaluation method based on joint entropy. Background technique [0002] With the rapid development of computers and the Internet, digital images are becoming more and more inseparable from people's daily life. When people use digital images, in order to achieve a certain goal, they often need to process images such as transmission, storage, compression, editing, etc., and these processes will inevitably affect the quality of digital images, resulting in varying degrees of digital image quality. Objective distortion degradation problem. So the objective evaluation of the degree of distortion of digital image quality came into being. In addition, in the fields of digital image processing, machine vision, and artificial intelligence, such as image fusion, image restor...

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
CPCG06T7/0002G06T2207/10024G06T2207/30168
Inventor 陈永利张欣阳钟京昊解梦思
Owner TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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