应用科学学报 ›› 2011, Vol. 29 ›› Issue (5): 473-482.doi: 10.3969/j.issn.0255-8297.2011.05.006

• 信号与信息处理 • 上一篇    下一篇

基于局部结构信息的图像质量评价空间汇集策略

王保云, 张荣, 尹东   

  1. 中国科学技术大学电子工程学与信息科学系,合肥230027
  • 收稿日期:2010-12-29 修回日期:2011-04-14 出版日期:2011-09-28 发布日期:2011-09-30
  • 通信作者: 作者简介:王保云,博士生,研究方向:数字图像处理、信号表示,E-mail: bywang@mail.ustc.edu.cn
  • 作者简介:作者简介:王保云,博士生,研究方向:数字图像处理、信号表示,E-mail: bywang@mail.ustc.edu.cn
  • 基金资助:

    基金项目:国家“973”重点基础研究发展计划基金(No.2010CB731904)资助

Spatial Pooling Strategies for Image Quality Assessment Based on Local Structural Information

WANG Bao-yun, ZHANG Rong, YIN Dong   

  1. Department of Electronic Engineering and Information Science, University of Science and Technology of China,
    Hefei 230027, China
  • Received:2010-12-29 Revised:2011-04-14 Online:2011-09-28 Published:2011-09-30

摘要:

该文从图像局部结构特性出发,提出一种基于图像局部结构信息的空间汇集算法. 首先对原始图像进行高斯模糊,提取局部结构信息并进行非零处理,进而形成汇集权重图. 通过对PSNR和SSIM的加权实验,验证了该汇集算法能够明显提高图像质量评价算法性能,并且对各种失真类型具有较好的适应性.

关键词: 图像质量评价, 结构信息, 视觉重要度, 空间汇集策略, 人类视觉系统

Abstract:

A spatial pooling strategies (SPS) for image quality assessment (IQA) is proposed, which obtain a weight map from local structural information (LSI) of the reference image. The reference image is first smoothed with a Gaussian kernel, and the LSI is extracted from the smoothed image. A weight map is derived from the LSI using a non-zero procedure. PSNR and SSIM obtained in the experiments show effectiveness of the proposed method for a wide range of image distortion types.

Key words:  image quality assessment, structural information, visual significance, spatial pooling strategy, human vision system(HVS)

中图分类号: