基于Riesz变换的结构相似度图像质量评价方法

卢彦飞; 张涛

doi:10.3788/YJYXS20153006.0992

您当前的位置：

首页 >

文章列表页 >

基于Riesz变换的结构相似度图像质量评价方法

成像技术与图像处理 | 更新时间：2020-08-12

- 基于Riesz变换的结构相似度图像质量评价方法
- Image quality assessment method via Riesz-transform based structural similarity
- 液晶与显示 2015年30卷第6期页码：992-999
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院大学北京,中国,100049
  3. 中国科学院苏州生物医学工程技术研究所,江苏苏州,215000
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目(No.61201117,No.61301042)();国家重大科学仪器设备开发专项(No.2011YQ040082)();国家科技支撑计划(No.
- DOI：10.3788/YJYXS20153006.0992
  中图分类号： TP394.1
- 收稿日期：2014-12-19，
  
  修回日期：2015-01-09，
  
  网络出版日期：2015-01-09，
  
  纸质出版日期：2015-12-05
- 稿件说明：
移动端阅览
卢彦飞, 张涛,. 基于Riesz变换的结构相似度图像质量评价方法[J]. 液晶与显示, 2015,30(6): 992-999

LU Yan-fei, ZHANG Tao,. Image quality assessment method via Riesz-transform based structural similarity[J]. , 2015,30(6): 992-999
卢彦飞, 张涛,. 基于Riesz变换的结构相似度图像质量评价方法[J]. 液晶与显示, 2015,30(6): 992-999 DOI： 10.3788/YJYXS20153006.0992.

LU Yan-fei, ZHANG Tao,. Image quality assessment method via Riesz-transform based structural similarity[J]. , 2015,30(6): 992-999 DOI： 10.3788/YJYXS20153006.0992.

摘要

不同的图像处理过程

会对图像引入各种各样的失真

如何对图像的质量进行评价成为一个热点问题。针对传统的基于像素差值统计的峰值信噪比方法及结构相似度方法与人眼主观评价不够符合的情况

本文提出了一种基于Riesz变换的结构相似度图像质量评价方法。该方法先将参考图像和失真图像进行一阶Riesz变换和二阶Riesz变换

并利用得到的5组对应特征图计算出5幅相似度图和5幅权重图

利用平均法进行融合得到最终的相似度图和权重图

然后加入原参考图像和失真图像的亮度比较项

得到最终的图像质量评价指标。在LIVE图像数据库上的实验表明

本文方法对于5种失真的质量预测准确性和一致性都很高

在交叉失真实验中

本文方法也优于结构相似度方法

PLCC和SROCC值达到了0.9482和0.9532。与几种公认较好的方法相比

本文方法能够更好地预测图像质量

更加符合人眼的主观感知。

Abstract

Various distortions will be introduced to images during different image processing procedures

and the assessment of image quality has become a hot topic. According to the fact that the traditional pixel-difference statistics-based PSNR method and structural similarity method cannot correlate well with human subjective evaluation

a novel image quality assessment method via Riesz-Transform based structural similarity is proposed. The method firstly applies 1st-order Riesz-Transform and 2nd-order Riesz Transform to the reference image and distorted image

and 5 groups of corresponding features maps are obtained to produce 5 similarity maps and 5 weighting maps. Then the average-method fusion is performed to get the final similarity map and weighting map. Lastly

the luminance comparison of the original reference image and distorted image is considered to get the final image quality index. The experiments on the LIVE database indicate that the proposed method has high prediction accuracy and consistency on all 5 distortion types. It also outperforms the SSIM method under cross-distortion conditions and the PLCC value and SROCC value reach 0.9482 and 0.9532 respectively. Compared with other state-of-the-art methods

the proposed method owns good predictive performance

which indicates better consistency with human subjective perception.

关键词

Keywords

references

Sheikh H R, Sabir M F, Bovik A C. A statistical evaluation of recent full reference image quality assessment algorithms[J]. IEEE Transactions on Image Processing, 2006, 15(11):3440-3451.

姚军财.基于人眼对比度敏感视觉特性的图像质量评价方法[J].液晶与显示, 2011,26(3):390-396. Yao J C. Image quality assessment method based on contrast sensitivity characteristics of human vision system[J]. Chinese Journal of Liquid Crystals and Displays, 2011, 26(3):390-396. (in Chinese).

Damera-Venkata N, Kite T D, Geisler W S, et al. Image quality assessment based on a degradation model[J]. IEEE Transactions on Image Processing, 2000, 9(4):636-650.

Chandler D M, Hemami S S. VSNR:A wavelet-based visual signal-to-noise ratio for natural images[J]. IEEE Transactions on Image Processing, 2007, 16(9):2284-2298.

Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.

Wang Z, Simoncelli E P, Bovik A C. Multiscale structural similarity for image quality assessment[C]. IEEE Conference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA:IEEE, 2003:1398-1402.

Wang Z, Li Q. Information content weighting for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(5):1185-1198.

Sheikh H R, Bovik A C, de Veciana G. An information fidelity criterion for image quality assessment using natural scene statistics[J]. IEEE Transactions on Image Processing, 2005, 14(12):2117-2128.

Sheikh H R, Bovik A C. Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006, 15(2):430-444.

Zhang L, Zhang L, Mou X Q, et al. FSIM:A feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8):2378-2386.

Zhang L, Zhang D, Mou X Q. RFSIM:A feature based image quality assessment metric using Riesz transforms[C]. 201017th IEEE International Conference on Image Processing, Hong Kong, China:IEEE, 2010:321-324.

Shnayderman A, Gusev A, Eskicioglu A M. An SVD-based grayscale image quality measure for local and global assessment[J]. IEEE Transactions on Image Processing, 2006, 15(2):422-429.

Chen G H, Yang C L, Xie S L. Gradient-based structural similarity for image quality assessment[C]. IEEE International Conference on Image Processing, Atlanta, GA, USA:IEEE, 2006:2929-2932.

Aja-Fernndez S, Estpar R S, Alberola-Lpez C, et al. Image quality assessment based on local variance[C]. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, New York City, USA:IEEE, 2006:4815-4818.

Sheikh H R, Wang Z, Cormack L, et al. LIVE image quality assessment database, release 2[OL]. http://live.ece.utexas.edu/research/quality.

VQEG. Final report from the video quality experts group on the validation of objective models of video quality assessment, Phase Ⅱ VQEG, Aug. 2003[OL]. Available:http://www.vqeg.org/,2014.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于特征符号化和Transformer的无参考图像质量评价方法

显示系统图像引擎的自适应色彩优化算法

基于小波加权的激光干扰效果评估

嵌入式设备立体图像显示技术研究