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

Contrast distortion image quality evaluation method fusing image entropy and structural similarity characteristics

A technology for image quality evaluation and structural similarity, applied in image analysis, image enhancement, image data processing and other directions, it can solve the problems of poor performance of color image distortion and degradation, image quality distortion and degradation, and achieve good evaluation results.

Pending Publication Date: 2022-03-11
TIANJIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the technical defects that the existing image quality evaluation system lacks the objective evaluation of the degree of distortion degradation of contrast-distorted color images and the poor performance of the existing contrast-distorted image quality evaluation methods, and proposes a Contrast-Distorted Image Quality Evaluation Method by Fusion of Image Entropy and Structural Similarity Features
The present invention uses this method to solve the problem of objective evaluation of the image quality distortion and degradation caused by the image in the process of image transmission, storage, compression, editing, etc., and the obtained evaluation data can truly reflect the difference between the distorted and degraded image and the standard image. difference, and it is consistent with the visual perception of the human eye

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
  • Contrast distortion image quality evaluation method fusing image entropy and structural similarity characteristics
  • Contrast distortion image quality evaluation method fusing image entropy and structural similarity characteristics
  • Contrast distortion image quality evaluation method fusing image entropy and structural similarity characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Select 1 reference image (standard) of the CSIQ (Categorical subjective image quality) database and 2 corresponding overall contrast reduction distorted images with different degrees of distortion, as the input of this embodiment, perform the contrast distortion image quality described in the present invention evaluation of. The CSIQ database contains 30 standard images and 866 distorted images. The distortion types of distorted images include JPEG compression, JPEG2000 compression, overall contrast reduction, additive Gaussian pink noise, additive Gaussian white noise and Gaussian blur. The CSIQ database also provides the average human perception error value (DMOS) of distorted images. The value range of DMOS is [0, 1]. The larger the DMOS, the lower the image quality and the worse the human perception effect.

[0046] image 3 is the selected reference image; Figure 4 It is a contrast distorted image with less distortion, and its DMOS is 0.090; Figure 5 It is a c...

Embodiment 2

[0056] Select 30 different reference images of the CSIQ database and 164 contrast distorted images corresponding thereto as the input of the present invention: 1 reference image and a plurality of distorted images corresponding to it form an input image group, and carry out the method described in the present invention The evaluation calculation of the distorted image quality; The evaluation process of the involved image quality is the same as embodiment one, after inspection, the evaluation data obtained by the evaluation method of the present invention and the DMOS data of the CSIQ database and the visual perception characteristics of the human eye is consistent.

[0057] According to the technical scheme of the present invention and figure 1 and figure 2 As shown in the process, the evaluation data of the above 164 images are acquired. In research, adopt " Pearson's linear correlation coefficient (PLCC) " and " Spearman's order correlation coefficient (SROCC) " index, ev...

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 contrast distortion image quality evaluation method fusing image entropy and structural similarity features, and belongs to the fields of image quality objective evaluation, image processing, machine vision and the like. According to the method, the image entropy and the structural similarity feature of the image are combined and fused, the defect that the image entropy feature is insensitive to the image structure is overcome, meanwhile, the structural feature and the entropy feature of the image are fused, and comprehensive quality evaluation is carried out on the image from the aspects of image pixel statistics and content structure; the problem of quantitative evaluation of image contrast distortion degradation in data processing processes of acquisition, transmission, conversion and the like is solved. According to the method, the evaluation process is not very complicated, the calculation efficiency is high, the accuracy is good, the image distortion can be well evaluated, and the evaluation data truly reflects the image degradation distortion degree and is consistent with the visual perception characteristics of human eyes; the method can meet the actual requirements of image quality distortion objective evaluation in the fields of image fusion, image enhancement, image recognition and the like.

Description

technical field [0001] The invention relates to the technical fields of objective evaluation of digital image quality, machine vision and artificial intelligence, and in particular to a contrast distortion image quality evaluation method that combines image entropy and structural similarity features. Background technique [0002] As we all know, digital images are inseparable from people's daily life, and their importance in people's work and life has become increasingly prominent. However, digital images are easily damaged in the process of collection and transmission, resulting in image distortion, resulting in insufficient aesthetics in display and essential loss of information content. Information is inconsistent. Therefore, in order to provide effective and real image processing data for image restoration, understanding, recognition and other applications, it is urgent to quantify and measure the distortion of the image. Image Quality Assessment (IQA) came into being a...

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
CPCG06T7/0002G06T2207/30168G06T2207/10024
Inventor 陈永利周艳华张欣阳
Owner TIANJIN UNIV OF SCI & TECH
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