计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (24): 205-210.

• 图形、图像、模式识别 • 上一篇    下一篇

医学图像质量评价中的梯度加权SSIM

段影影,陈武凡,冯前进,马建华   

  1. 南方医科大学 生物医学工程学院,广州 510515
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-08-21 发布日期:2011-08-21

Gradient-weighted SSIM based medical image quality assessment

DUAN Yingying,CHEN Wufan,FENG Qianjin,MA Jianhua   

  1. School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-21 Published:2011-08-21

摘要: Zhou Wang等人提出了著名的图像客观质量评价方法:结构相似度(SSIM),其理论基础是人眼视觉系统能高度自适应地提取场景中的结构信息,大量实验证明SSIM的评价性能多优于PSNR(或MSE)。然而,由于视觉掩盖效应的影响,且SSIM规避了HVS底层视觉特性,直接导致SSIM的评价常与主观评价不符。在深入研究SSIM算法的基础上,根据人眼视觉的掩盖效应之特性,提出图像中不同区域的失真程度引导的权值设计方案:基于梯度加权的SSIM图像质量评价方法(GWSSIM)。实验结果表明,GWSSIM的图像质量评价准确性高于PSNR和SSIM,尤其适用于医学图像。

关键词: 结构相似(SSIM), 梯度加权, 视觉掩盖效应

Abstract: Structure Similarity(SSIM) as a well-known objective image quality assessment is proposed by Zhou Wang.SSIM assumes that human visual perception is highly adapted for extracting structure information from a scene.Compared with PSNR or MSE,SSIM has a strong advantage which has been proved in many different image quality assessments.But,due to the HVS characteristics of the underlying visual are neglected,SSIM has some drawbacks such as failing in blurred image measurement.In this study,based on the visual masking effect it introduces an improved SSIM method which is called as Gradient-Weighted SSIM(GWSSIM).GWSSIM performs different regions of image which are weighted with different values.Experimental results show that GWSSIM has a better performance than both PSNR and SSIM,especially for medical image quality assessments.

Key words: Structural Similarity(SSIM), gradient-weighted, visual masking effect