期刊文献+

快速提升的结构相似度IQA算法 被引量:3

Fast Lifting IQA Algorithm of the Structure Similarity Index
在线阅读 下载PDF
导出
摘要 客观图像质量评价(IQA)的目的是设计与主观评价算法尽可能一致的数学模型来度量图像的质量.针对结构相似度(SSIM)和其他一些算法的局限性,考虑到梯度可以反映图像的边缘纹理等结构信息,提出一种快速的全参考型IQA算法,即提升的梯度加权结构相似度(GWL-SSIM)算法.首先定义图像局部块的广义梯度;然后利用其相似性及图像对比度相似性和结构相似性得到局部质量的特征映射图;最后采用广义梯度加权的池化策略得到IQA模型,广义梯度能很好地刻画视觉感知系统的非线性属性,而加权策略模拟了其对图像不同成分感知的差异性.在6个公开数据库中进行数值实验的结果表明,GWL-SSIM算法计算效率高,并取得了与目前流行算法相当的评价效果. Image quality assessment(IQA)aims to design mathematical models for measuring an imagequality well consistent with subjective evaluations.Considering both the limitations of structure similarity(SSIM)index and other methods,and the advantages of the gradient on characterizing the edge and textureinformation of an image,we put forward a kind of fast full-reference IQA algorithm,namely gradientweighted lifting SSIM(GWL-SSIM)method.Firstly,we define the generalized gradient of local image block.Then employ the generalized gradient similarity,contrast similarity and structural similarity to obtain a featuremapping image of local quality.Finally,we adopt the weighted pooling strategy by generalized gradientinformation to obtain an image evaluation model.In our algorithm,the generalized gradient well describesthe nonlinearity of human visual system(HVS)for image perception,while the weighted strategy simulatesthe diversity how HVS perceive the different ingredients of an image.Numerical experiments,performed onsix public databases,demonstrate that GWL-SSIM can achieve high computational efficiency and have aconsiderable evaluation result compared with state-of-the-art IQA metrics.
作者 高丽霞 刘国军 张选德 Gao Lixia;Liu Guojun;Zhang Xuande(School of Mathematics and Statistics, Ningxia University, Yinchuan 750021)
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2017年第7期1314-1323,共10页 Journal of Computer-Aided Design & Computer Graphics
基金 国家自然科学基金(61461043 61362029) 宁夏自然科学基金(NZ1616)
关键词 图像质量评价 广义梯度特征 结构相似度 池化策略 image quality assessment generalized gradient features structural similarity pooling strategy
作者简介 高丽霞(1991—),女,硕士研究生,主要研究方向为数字图象处理、图像质量评价;刘国军(1978—),男,博士,教授,硕士生导师,论文通讯作者,主要研究方向为小波分析和偏微分方程图像处理及应用、图像质量评价(liugj@nxu.edu.cn);张选德(1979—),男,博士,副教授,硕士生导师,主要研究方向为图像处理、稀疏表示理论、低秩逼近、图像质量评价
  • 相关文献

参考文献2

二级参考文献16

  • 1梁亚玲,杨春玲,余英林,杜明辉.基于人眼视觉特性的任意形状ROI编码[J].华南理工大学学报(自然科学版),2005,33(3):44-49. 被引量:4
  • 2许志良,谢胜利.一种基于MRF的自适应块效应去除算法[J].华南理工大学学报(自然科学版),2005,33(7):15-19. 被引量:3
  • 3Mannos J L,Sakrison D J.The effects of a visual fidelity criterion on the encoding of images[J].IEEE Trans on Information Theory,1974,20(4):525-536.
  • 4Sakrison D J.On the role of the observer and a distortion measure image transmission[J].IEEE Trans on COM,1977,25(11):1 251-1 267.
  • 5Lubin J.A visual discrimination model for imaging system design and evaluation[M]∥Pelied E.Vision Models for Target Detection and Recognition.New York:World Scientific Publishing Co Pte Ltd,1995.
  • 6VQEG.Final report from the video quality experts group on the validation of objective models of video quality assessment[EB/OL].(2000-03-05).http:∥www.vqeg.org/.
  • 7Wang Zhou,Bovik A C,Lu Li-gang.Why is image quality assessment so difficult?[C]∥Proc of IEEE Int Conf on Acoustics,Speech,and Signal Processing.Orlando:[s.n.],2002:IV-3 313-IV-3 316.
  • 8Wang Zhou,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Trans on Image Processing,2004,13(4):600-612.
  • 9Pan Xiao-zhou,Yang Chun-ling,Xie Sheng-li.An improved structural similarity for image quality assessment[C]∥Proc of SPIE.Wuhan:[s.n.],2005:60441I-1-6044l I-9.
  • 10Cadik M,Slavik P.Evaluation of two principal approaches to objective image quality assessment[C]∥Proc of the 8th International Conference on Information Visualisation.London:IEEE Computer Society,2004:513-518.

共引文献49

同被引文献8

引证文献3

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部