Image Perceptual Quality Assessment Using Contourlet Transform

SUN Yu-bao; FEI Xuan; WEI Zhi-hui; XIAO Liang; HU Xi-yuan; LV Zhan-qiang

您当前的位置：

首页 >

文章列表页 >

Image Perceptual Quality Assessment Using Contourlet Transform

更新时间：2025-07-16

- Image Perceptual Quality Assessment Using Contourlet Transform
- Acta Electronica Sinica Vol. 39, Issue 3, Pages: 649-655(2011)
- 作者机构：
  
  1. 南京理工大学计算机科学与技术学院模式识别与智能系统实验室,江苏,南京,210094
  2. 中国人民解放军总参谋部第六十研究所训练科研处,江苏,南京,210016
  3. 南京理工大学计算机科学与技术学院模式识别与智能系统实验室江苏南京,210094
  4. 中国人民解放军总参谋部第六十研究所训练科研处江苏南京,210016
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2011
- 稿件说明：
移动端阅览
SUN Yu-bao, FEI Xuan, WEI Zhi-hui, et al. Image Perceptual Quality Assessment Using Contourlet Transform[J]. Acta Electronica Sinica, 2011, 39(3): 649-655.
DOI：

SUN Yu-bao, FEI Xuan, WEI Zhi-hui, et al. Image Perceptual Quality Assessment Using Contourlet Transform[J]. Acta Electronica Sinica, 2011, 39(3): 649-655. DOI：

摘要

图像感知质量评价是图像信息工程的基础技术之一.结合人类视觉系统(HVS)的感知特性

在Contourlet变换域建立了一个新的可计算JND门限模型

该模型综合考虑了HVS的空间频率敏感性、方向敏感性、对比度掩盖与邻域掩盖特性.由于邻域掩盖模型的引入

能够有效鉴别图像中平滑、边缘与纹理结构区域对失真的不同掩盖强度

实现更加精确的掩盖阈值计算.借助于建立的JND模型

定义每个系数的感知误差

进而建立了感知质量评价标准HVSNR.实验结果表明该定量评价标准能够有效匹配人类的视觉感觉.

Abstract

Image perceptual quality assessment is a key problem in image processing engineering.According to the perceptual characters of Human Visual System (HVS)

a Just Noticeable Distortion (JND) threshold model is constructed using contourlet transform

which can well qualify spatial frequency sensitivity

orientation sensitivity

contrast masking and neighborhood masking effects of HVS.As a result of taking account of neighborhood masking additionally

this JND model can distinguish the different masking intensity of smoothness

edge and texture domain

and implement more accurate JND threshold.Based on our JND threshold model

the perceptual error between contourlet coefficients is defined

and then a quantitative perceptual quality metric HVSNR is proposed.Experiments demonstrate that our metric can provide quality evaluation well correlated with those given by human observers.

关键词

Keywords

references

Views

1223

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Non-Redundant Laplacian Pyramid Design Based on Directional Filter Bank

Vein Image Acquisition Method Based on Quality Assessment Model Without Reference

Related Author

YANG Yang

PENG Yu-hua

LIU Yun-xia

XU Jian-hua

JIA Xu

CAO Yu-dong

SUN Fu-ming

CUI Jian-jiang

Related Institution

School of Information Science and Engineering,Shandong University

National Key Laboratony for Electronic Measurement Technology

School of Information Science and EngineeringShandong UniversityJinanShandong 250100China

National Key Laboratony for Electronic Measurement TechnologyQingdaoShandong 266555China

School of Electronics and Information Engineering, Liaoning University of Technology

⁰