基于结构相似的小波域图像质量评价方法的研究  

Research on Image Quality Assessment in Wavelet Domain Based on Structural Similarity

作　　者：杨春玲[1] 高文瑞[1] 

机构地区：[1]华南理工大学电子与信息学院,广东广州510640

出　　处：《电子学报》2009年第4期845-849,共5页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60402015);广东省自然科学基金(No.06025642)

摘　　要：小波域的图像处理已经成为图像处理领域的重要组成部分,研究能嵌入在小波域图像处理算法中的图像质量评判方法显得至关重要.空间域结构相似度SSIM具有计算简单、与主观评分相关性高等优点.本文通过对小波域图像结构特性的研究,提出了小波域结构相似度(DWTSSIM)的图像质量评价方法.实验结果表明DWTSSIM比SSIM更加符合人眼的视觉特性,可以更好地评判图像质量,并且能容易地嵌入在小波域图像处理算法中,在图像处理过程中指导或调节算法.As image processing in wavelet domain has been an important part of image processing,it is very important to find an assessment model of image quality that can be used in image processing algorithms based on discrete wavelet transform （DWT）. The SSIM（Structural Similarity）,an image quality assessment method,is proposed in pixel domain based on structural information, and it has excellent performance of simplicity and well correlation with subjective evaluation. Based on the research of image strucural properties in wavelet domain, in this paper we propose an image quality assessment method that is called the Discrete Wavelet Transform based Structural Similarity（DWTSSIM）. The result shows that the proposed DWTSSIM correlates well with the judgment of human observers. And it can easily be embedded in image processing algorithms in wavelet domain, to guide or regulate the processing algorithms.

关 键 词：图像质量评价 结构相似度(SSIM) 人眼视觉系统(HVS) 小波域结构相似度(DWTSSIM) 

分 类 号：TN911.73[电子电信—通信与信息系统]