首页 > 论文 > 液晶与显示 > 33卷 > 10期(pp:877-883)

基于稀疏表示的SOM多失真图像质量评价方法

Multi-distorted image quality assessment algorithm based on sparse representation and SOM

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对非线性回归下客观评分与主观评分一致性差的问题,本文提出一种基于稀疏表示的SOM多失真图像质量评价方法。首先,将参考图像及失真图像应用独立变量分析进行稀疏化表示,应用稀疏表示下的参考图像与失真图像间的结构相似度描述失真图像的质量,再使用SOM聚类算法和交叉验证方法提高非线性回归下的客观评分与主观评分之间的一致性。最后,在LIVE2, TID2013及IVC数据库中的实验结果显示,所提评价模型性能优越;3种数据库的平均结果说明,该文方法的总体性能高于现有的经典算法,表明该文方法能够很好地反映图像的视觉感知效果。通过对比时间效率,该方法基本能够满足实际要求,具有较高的适用性。

Abstract

Due to the problem of poor consistency between objective score in nonlinear regression and subjective scores, a multi-distorted image quality assessment method based on sparse representation and SOM is presented in this paper. Firstly, the reference image and the multi-distorted image are represented sparsely by independent component analysis, and the structural similarity index between the reference image and the distorted image under the sparse representation is computed to describe the quality of multi-distorted image. Secondly, the consistency between objective score in nonlinear regression and subjective score is improved by the SOM and cross-validation algorithms. Finally, the experimental results in LIVE2, TID2013 and IVC databases show that the proposed evaluation model has good performance. The average result of 3 kinds of databases shows that the overall performance of the method is higher than the existing classical algorithm, which indicates that the proposed method can reflect the visual perception of the image well. Comparison with the time efficiency, the proposed algorithm can basically meet the practical demand and has high practicability.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/yjyxs20183310.0877

所属栏目:图像处理

收稿日期:2018-04-04

修改稿日期:2018-07-06

网络出版日期:--

作者单位    点击查看

王春哲:中国科学院大学,北京 100049中国科学院 复杂航天系统电子信息技术重点实验室,北京 100190
安军社:中国科学院 复杂航天系统电子信息技术重点实验室,北京 100190
姜秀杰:中国科学院 复杂航天系统电子信息技术重点实验室,北京 100190
李杰:长春大学 信息工程学院,吉林 长春 130022
张羽丰:中国科学院大学,北京 100049中国科学院 复杂航天系统电子信息技术重点实验室,北京 100190

联系人作者:安军社(anjunshe@nssc.ac.com)

备注:王春哲(1989-),男,吉林松原人,博士研究生,2012年于长春大学获得学士学位,2015年于长春理工大学获得硕士学位,现为中国科学院大学博士研究生,主要从事深度学习及目标检测方面的研究。E-mail: wangchunzhe163@sina.com

【1】王春哲,李杰,李明晶,等.一种多扭曲失真图像的质量评价方法[J]. 液晶与显示,2015,30(4):681-686.
WANG C Z, LI J, LI M J, et al. Image quality assessment algorithm for multi-distorted image [J]. Chinese Journal of Liquid Crystals and Displays, 2015, 30(4): 681-686. (in Chinese)

【2】范媛媛,沈湘衡,桑英军.基于对比度敏感度的无参考图像清晰度评价[J]. 光学 精密工程,2011,19(10):2485-2493.
FAN Y Y, SHEN X H, SANG Y J. No reference image sharpness assessment based on contrast sensitivity [J]. Optics and Precision Engineering, 2011, 19(10): 2485-2493. (in Chinese)

【3】陈勇,李愿,吕霞付,等.视觉感知的彩色图像质量积极评价[J]. 光学 精密工程,2013,21(3):742-750.
CHEN Y, LI Y, LV X F, et al. Active assessment of color image quality based on visual perception [J]. Optics and Precision Engineering, 2013, 21(3): 742-750. (in Chinese)

【4】徐海勇,郁梅,骆挺,等.基于非负矩阵分解的彩色图像质量评价方法[J]. 电子与信息学报,2016,38(3):578-585.
XU H Y, YU M, LUO T, et al. A color image quality assessment method based on non-negative matrix factorization [J]. Journal of Electronics & Information Technology, 2014, 24(10): 1330-1333. (in Chinese)

【5】刘建磊.结合局部特征的无参考彩色图像质量评价[J]. 光学 精密工程,2016,24(5):1176-1184.
LIU J L. No-reference color image quality assessment based on local features [J]. Optics and Precision Engineering, 2016, 24(5): 1176-1184. (in Chinese)

【6】LI Y M, PO L M, FENG L T, et al. No-reference image quality assessment with deep convolutional neural networks[C]//Proceedings of 2016 IEEE International Conference on Digital Signal Processing. Beijing, China: IEEE, 2017: 685-689.

【7】徐云生,尹东.一种基于Contourlet变换的图像质量评价算法[J]. 电子技术,2010,47(7):23-26.
XU Y S, YIN D. An image quality assessment algorithm based on Contourlet transform[J]. Electronic Technology, 2010, 47(7): 23-26. (in Chinese)

【8】GUHA T, NEZHADARYA E, WARD R K. Sparse representation-based image quality assessment[J]. Signal Processing: Image Communication, 2014, 29(11): 1138-1148.

【9】HYVRINEN A, OJA E. Independent component analysis: algorithms and applications[J]. Neural Networks, 2000, 13(4-5): 411-430.

【10】KOHONENT. Self-organized formation of topologically correct feature maps[J]. Biological Cybernetics, 1982, 43(1): 59-69.

【11】SHEIKH H R, WANG Z, CORMACK L, et al. LIVE image quality assessment database release 2[EB/OL]. http://live.ece.utexas.edu/research/quality/live_multidistortedimage.htm, 2014.

【12】CALLET P L, AUTRUSSEAU F. Subjective quality assessment IRCCyN/IVC database[J]. 2005.

【13】PONOMARENKO N, JIN L, IEREMEIEV O, et al. Image database TID2013: Peculiarities, results and perspectives[J]. Signal Processing: Image Communication, 2015, 30: 57-77.

【14】MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12): 4695-4708.

引用该论文

WANG Chun-zhe,AN Jun-she,JIANG Xiu-jie,LI Jie,ZHANG Yu-feng. Multi-distorted image quality assessment algorithm based on sparse representation and SOM[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(10): 877-883

王春哲,安军社,姜秀杰,李杰,张羽丰. 基于稀疏表示的SOM多失真图像质量评价方法[J]. 液晶与显示, 2018, 33(10): 877-883

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF