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

No-reference noise image quality evaluation method and system

A technology for image quality evaluation and reference noise, which is applied in the field of image processing and can solve problems such as inaccurate evaluation of severely distorted images

Inactive Publication Date: 2017-07-28
WUHAN UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0029] The purpose of the present invention is to solve the problem of inaccurate evaluation of severely distorted images by the current image quality evaluation method. Under the situation of no reference noise based on BEMD decomposition and Riesz transformation, a kind of no-reference noise image based on BEMD decomposition and Riesz transformation is provided Quality Evaluation Method and System

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
  • No-reference noise image quality evaluation method and system
  • No-reference noise image quality evaluation method and system
  • No-reference noise image quality evaluation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0136] Such as figure 1 , the implementation of a reference noise-free image quality evaluation method provided in the embodiment includes the following processing procedures:

[0137] Step S1, performing BEMD decomposition and Riesz transformation on the image to be tested;

[0138] Step S2, performing weighted summation on the results of step S1 by using the visual contrast sensitivity function to obtain the feature map of the denoised image;

[0139] Step S3, using the feature maps of the image to be tested and the denoised image to perform similarity calculation and weighted summation to obtain an evaluation result.

[0140] Such as figure 2 As shown, the step S1, performing BEMD decomposition and Riesz transformation on the image to be tested, comprises the following steps:

[0141] Step1.1, for the image to be tested, perform BEMD decomposition in the two-dimensional empirical mode:

[0142] Step A. For the two-dimensional image signal f (x, y), x=1, ..., M, y=1, .....

Embodiment 2

[0186] It should be noted that Embodiment 1 is a method embodiment, and Embodiment 2 is a system embodiment. This embodiment 2 and method embodiment 1 belong to the same technical concept. For the content that is not described in detail in this embodiment 2, please refer to the method Example 1.

[0187] During specific implementation, the method provided by the present invention can realize the automatic operation process based on software technology, and can also realize the corresponding system in a modular manner.

[0188] Such as Figure 5 As shown, the present invention provides a reference noise-free image quality evaluation system, including the following modules,

[0189] The first module is used to perform BEMD decomposition and Riesz transformation on the image to be tested;

[0190] The second module is used to carry out weighted summation using the visual contrast sensitivity function to the results of the first module to obtain the feature map of the denoising ...

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 no-reference noise image quality evaluation method and system, and belongs to the image processing field. The no-reference noise image quality evaluation method includes the steps: performing BEMD (Bidimensional Empirical Mode Decomposition) and Riesz transformation on an image to be detected; utilizing a visual contrast sensitivity function to perform weighting sum and obtaining the characteristic graph of the de-noised image; and utilizing the image to be detected and the characteristic graph of the de-noised image to perform similarity calculation and weighting sum, and finally obtaining the evaluation result. The no-reference noise image quality evaluation method evaluates the no-reference noise image quality through BEMD decomposition and Riesz transformation; compared with an image noise estimation method, the no-reference noise image quality evaluation method has better evaluation effect, and the correlation between the evaluation result and the subjective evaluation result is greater and the error is smaller; the algorithm performs an index test on three databases, LIVE, CSIQ and TID2008, and performs a point diagram experiment on the LIVE database at the same time; and the experimental result represents that the BRIQ algorithm shows good performance on evaluation of the noise image.

Description

technical field [0001] The invention relates to a reference noise-free image quality evaluation method and system, belonging to the field of image processing. Background technique [0002] With the vigorous development of digital technology and multimedia communication, digital images, as an important element of information expression and communication, have been widely used. However, in the process of image acquisition, storage, transmission, display, etc., it is inevitable to introduce some interference factors, such as noise, blur, data loss, etc., which will cause the degradation of image quality. [1] . The quality of image quality directly affects people's subjective feelings and information acquisition. How to establish an effective image quality evaluation mechanism in the fields of video transmission, character recognition, security monitoring, and medicine is of great significance. Image quality assessment (IQA ) research came into being [2][3] . Image quality e...

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
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/30168
Inventor 杨光义彭鑫港蔡静宜王子桥孙经纬刘潇
Owner WUHAN UNIV
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