Image Quality Assessment Based on Structural Information Extraction

YE Sheng-nan; SU Kai-na; XIAO Chuang-bai; DUAN Juan

您当前的位置：

首页 >

文章列表页 >

Image Quality Assessment Based on Structural Information Extraction

更新时间：2025-07-16

- Image Quality Assessment Based on Structural Information Extraction
- Acta Electronica Sinica Vol. 36, Issue 5, Pages: 856-861(2008)
- 作者机构：
  
  北京工业大学计算机学院,北京,100022
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2008
- 稿件说明：
移动端阅览
YE Sheng-nan, SU Kai-na, XIAO Chuang-bai, et al. Image Quality Assessment Based on Structural Information Extraction[J]. Acta Electronica Sinica, 2008, 36(5): 856-861.
DOI：

YE Sheng-nan, SU Kai-na, XIAO Chuang-bai, et al. Image Quality Assessment Based on Structural Information Extraction[J]. Acta Electronica Sinica, 2008, 36(5): 856-861. DOI：

摘要

结构相似性理论是一种关于图像质量评价的新思想.与自底向上地模拟人眼视觉系统(HVS)低阶的组成结构不同

结构相似性理论自顶向下地模拟HVS的整体功能.作为结构相似性理论的一个实现

结构相似度(SSIM)指数有着简单高效的优点

但SSIM在交叉失真类型和失真严重时的准确性不够好.本文将结构信息重新解释为图像中能量足够大的中高频成分

从新的角度将SSIM理解为一种更好的局部误差度量方式.提出一种基于结构信息提取(SIExt)的图像质量评价方法

将图像中的结构信息分离出来给予较大的权重

并用SSIM作为误差度量估计局部失真.实验结果表明

SIExt比PSNR和SSIM等方法有更好的准确性.

Abstract

The philosophy of structural similarity is a new idea about image quality assessment.Different from the traditional paradigm which modeling the low level composition of Human Visual System (HVS) bottom-up

the new philosophy modes the functionality of the overall HVS from top to down.As an implementation of the new philosophy

the Structural SIMilarity (SSIM) index is simple and efficient.However

SSIM fails in measuring the badly distorted images and images with cross distortion types.In this paper

we interpret the structural information as the mid and high frequencies with enough energy

and regard the SSIM index as a better distortion measure of local areas.Then

a new image quality index based on Structural Information Extraction (SIExt) is proposed.In SIExt

structural information is separated from image and given higher weight

and SSIM is used as an error measure to estimate local distortions.Experimental results show that the proposed SIExt can assess the quality of images more accurate than PSNR and SSIM.

关键词

Keywords

references

Views

3026

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dual-Channel Deep Image Prior for Image Denoising

Review and Prospect of Full Reference Image Quality Assessment

Image Perceptual Hashing Based on Human Visual System

Related Author

GAO Wen-rui

YANG Chun-ling

XIE Sheng-li

CHEN Guan-hao

YANG Chun-ling

CHEN Xiao-jun

CHENG Xiao-hui

XU Shao-ping

Related Institution

School of Electronic and Information Engineering, South China University of Technology

School of Mathematics and Computer Sciences， Nanchang University

Infectious Disease Hospital Affiliated to Nanchang University

School of Electrical and Control Engineering， Shaanxi University of Science and Technology

⁰