No-Reference Image Quality Assessment Based on Structure Information and Luminance Statistics

SHEN Jun-min; LI Jun-feng; DAI Wen-zhan

doi:10.3969/j.issn.0372-2112.2016.04.008

您当前的位置：

首页 >

文章列表页 >

No-Reference Image Quality Assessment Based on Structure Information and Luminance Statistics

更新时间：2025-07-16

- No-Reference Image Quality Assessment Based on Structure Information and Luminance Statistics
- Acta Electronica Sinica Vol. 44, Issue 4, Pages: 804-812(2016)
- 作者机构：
  
  1. 浙江理工大学电子信息工程系,浙江,杭州,310018
  2. 浙江理工大学自动化系,浙江,杭州,310018
  3. 浙江工商大学电子信息工程系,浙江,杭州,310018
  4. 浙江理工大学电子信息工程系,浙江,杭州,310018
  5. 浙江理工大学自动化系,浙江,杭州,310018
  6. 浙江工商大学电子信息工程系,浙江,杭州,310018
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61374022);Non-profit Technology Application Research Project of Zhejiang Province (No.2014C33109)
- DOI：10.3969/j.issn.0372-2112.2016.04.008
  CLC： TN919.81
- Published Online：25 April 2016，
  
  Published：2016
- 稿件说明：
移动端阅览
SHEN Jun-min, LI Jun-feng, DAI Wen-zhan. No-Reference Image Quality Assessment Based on Structure Information and Luminance Statistics[J]. Acta Electronica Sinica, 2016, 44(4): 804-812.
DOI：

SHEN Jun-min, LI Jun-feng, DAI Wen-zhan. No-Reference Image Quality Assessment Based on Structure Information and Luminance Statistics[J]. Acta Electronica Sinica, 2016, 44(4): 804-812. DOI： 10.3969/j.issn.0372-2112.2016.04.008.

摘要

基于非下采样Contourlet变换(Nonsubsampled Contourlet Transform

NSCT)子带系数间的结构相关性

本文提出了一种通用的无参考图像质量评价方法.首先

利用互信息分析NSCT子带系数间的相关性

确定出相关性比较强的子带系数;其次

分别计算这些子带系数间的结构信息比较算子

以此作为描述图像结构相关性的统计特征;进而

结合空间域亮度均值减损对比归一化(Mean Subtracted Contrast Normalized

MSCN)系数及其邻域系数的统计特征

分别构造相应的无参考图像质量评价模型和图像失真类型识别模型;最后

在LIVE等图像质量评价数据库上进行了大量的实验仿真.仿真结果表明

评价模型的评价结果与人类主观评价具有非常高的相关性

与当今主流评价算法相比非常具有竞争性.

Abstract

Based on the correlation between subband coefficients of nonsubsampled contourlet transform(NSCT)

a general-purpose no-reference image quality assessment(NR-IQA)method is proposed.Firstly

the correlation between NSCT subband coefficients was analyzed using mutual information and the subband coefficients with strong correlation were determined.Secondly

the structure comparison operator of those subband coefficients were calculated respectively and used to describe the statistics characteristic of image structure information.Moreover

a no-reference image quality assessment model and an image distortion type recognition model were constructed by combining the statistical features of the mean subtracted contrast normalized(MSCN)coefficients and the structural similarity of NSCT coefficients.Finally

a large number of simulation experiments were carried out in the LIVE image quality evaluation database.The simulation results show that this method is suitable for many common image distortion types and correlates well with the human judgments of image quality

and the assessment model is competitive with the nowadays' mainstream evaluation method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SAR Image Despeckling Based on the Estimation of Speckle Variance in Nonsubsampled Contourlet Domain

SAR Image Despeckling Based on Local Gaussian Model and MAP in NSCT Domain

The Nonsubsampled Contourlet Transform in Multisensor Images Fusion

Fusion of Infrared and Visible Images Based on Edge Feature and Adaptive PCNN in NSCT Domain

Related Author

FONT

SHA Yu-heng

LIU Fang

JIAO Li-cheng

CHANG Xia

Verdana

FONT face

BU Xiao-ming

Related Institution

(Institute of Intelligent Information Processing and Key Laboratory of Intelligent Perception andImage Understanding of Ministry of Education, Xidian University,,,)

Institute of Intelligent Information Processing,Xidian University

Department of Mathematics,Northwest University

Institute of Intelligent Information ProcessingXidian UniversityXi’anShaanxi 710071China

Department of MathematicsNorthwest UniversityXi’anShaanxi 710069China

⁰