基于相关性的JPEG高压缩图像峰值信噪比盲估计

doi:10.3969/j.issn.1000-3428.2017.08.043

计算机工程

基于相关性的JPEG高压缩图像峰值信噪比盲估计

陆敏俊¹,王慈²

(1.上海交通大学电子工程系,上海 200240; 2.华东师范大学计算机科学技术系,上海 200241)

收稿日期:2016-06-23 出版日期:2017-08-15 发布日期:2017-08-15
作者简介:陆敏俊(1992—),男,硕士研究生,主研方向为图像处理;王慈,副教授、博士后。
基金项目:
国家自然科学基金面上项目“基于内容的视频事件检测与描述研究”(61375016)。

Blind Estimation of Peak Signal to Noise Ratio for JPEG Highly Compressed Images Based on Correlation

LU Minjun¹,WANG Ci²

(1.Department of Electrical Engineering,Shanghai Jiaotong University,Shanghai 200240,China; 2.Department of Computer Science and Technology,East China Normal University,Shanghai 200241,China)

Received:2016-06-23 Online:2017-08-15 Published:2017-08-15

摘要/Abstract

摘要： 量化噪声是JPEG图像压缩过程中产生的主要失真,在图像质量评估时需要对其大小进行估计。针对峰值信噪比(PSNR)估计方法在实际应用时终端用户无法获取原始图像的限制,基于图像空域相关性,引入JPEG压缩图像的斜率均方差和最大非零离散余弦变换系数的位置作为可测特征量,利用训练图像进行机器学习得到训练模型,将测试图像进行解析得到图像PSNR盲估计结果。实验结果表明,该PSNR估计结果优于目前流行的峰值信噪比盲估计方法。

关键词: 量化噪声, JPEG图像, 峰值信噪比, 图像相关性, 斜率均方差, 机器学习

Abstract: Quantization noise is one of thedominant distortions of JPEG image compression,so its amplitude usually needs to be estimated for image quality assessment.Meanwhile,Peak Signal to Noise Ratio(PSNR) estimation method cannot get the original image in the practical applications,so Mean Squared Difference Slope(MSDS) and the position of maximum nonzero Discrete Cosine Transform(DCT) coefficient are introduced as the measurable characteristics based on image spatial correlation.Some images as well as their PSNR are trained to produce the PSNR estimation model,and the test image is fed into the model to estimate its PSNR.Experimental results show that the proposed algorithm is superior to the existing blind PSNR estimation algorithms.

Key words: quantization noise, JPEG image, Peak Signal to Noise Ratio(PSNR), image correlation, Mean Squared Difference Slope(MSDS), machine learning

中图分类号:

TP391.41

陆敏俊,王慈. 基于相关性的JPEG高压缩图像峰值信噪比盲估计[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2017.08.043.

LU Minjun,WANG Ci. Blind Estimation of Peak Signal to Noise Ratio for JPEG Highly Compressed Images Based on Correlation [J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.08.043.

参考文献

参考文献［1］Anush M K,Kalpana S,Rajiv S,et al.Wireless Video Quality Assessment:A Study of Subjective Scores and Objective Algorithms ［J］.IEEE Transactions on Circuits and Systems for Video Technology,2010,20(4):587-599. ［2］Chen Xiaolin,Zhang Rui,Zheng Shibao.Image Quality Assessment Based on Local Edge Direction Histo-gram［C］//Proceedings of IEEE International Conference on Image Analysis and Signal Processing.Washington D.C.,USA,IEEE Press,2011:108-112. ［3］Ichigaya A,Kurozumi M,Hara N,et al.A Method of Estimating Coding PSNR Using Quantized DCT Coefficients［J］.IEEE Transactions on Circuits Systems Video Technology,2006,16(2):251-259. ［4］Brandao T,Queluz M P.No-reference Image Quality Assessment Based on DCT-domain Statistics［J］.Signal Processing,2008,88(4):822-833. ［5］景麟,王宏远,马泳.基于拉普拉斯分布模型的快速DCT 算法［J］.电视技术,2008,32(11):16-19. ［6］Lam E Y,Goodman J W.A Mathematical Analysis of the DCT Coefficient Distributions for Images［J］.IEEE Transactions on Image Processing,2000,9(10):1661-1666. ［7］董皓远,方向忠.基于图像先验知识的量化噪声盲估计算法［J］.计算机工程,2010,36(11):195-197. ［8］Pao I M,Sun Ming Ting.Modeling DCT Coefficients for fast Video Encodings［J］.IEEE Transactions on Circuits and Systems for Video Technology,1999,9(4):608-616. ［9］Minami S,Zakhor A.An Optimization Approach for Removing Blocking Effects in Transform Coding［J］.IEEE Transactions on Circuits System,1995,5:74-82. ［10］沈诗文.量化噪声建模及其在去块效应算法中的应用［D］.上海:上海交通大学,2011. ［11］程燕.图像超分辨率重建关键技术的研究［D］.上海:上海交通大学,2007. ［12］Robertson M A,Stevenson R L.DCT Quantization Noise in Compressed Images［J］.IEEE Transactions on Circuits and Systems for Video Technology,2005,15(1):27-38. ［13］Yang Gao,Tan Yap Peng.Blind PSNR Estimation Using Shifted Blocks for JPEG Images［C］//Proceedings of ISCAS’11.Washington D.C.,USA:IEEE Press,2011:216-225. ［14］Sheikh H R,Wang Z,Cormack L,et al.IVE Image Quality Assessment Database Release 2［EB/OL］.［2015-12-21］.http://live.ece.utexas.edu/research/quality. ［15］Anish M,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. 编辑索书志

[1]	张凯, 周德云, 杨振, 潘潜. 基于自适应谐振理论的武器目标分配快速决策算法[J]. 计算机工程, 2020, 46(9): 283-291,297.
[2]	张杰, 沈苏彬. 一种适用于物联网的在线GP-ELM算法[J]. 计算机工程, 2020, 46(6): 314-320.
[3]	梁猛, 史晓霜. 基于二阶Newton插值的莫尔条纹消除算法[J]. 计算机工程, 2020, 46(5): 259-266.
[4]	张春富, 王松, 吴亚东, 王勇, 张红英. 基于GA_Xgboost模型的糖尿病风险预测[J]. 计算机工程, 2020, 46(3): 315-320.
[5]	潘维蔚, 康凯, 张武雄, 王海峰. 基于WiFi的室内定位准确率改进算法[J]. 计算机工程, 2020, 46(2): 207-213.
[6]	李慧, 张南南, 曹卓, 郑海, 陈湘萍. 基于机器学习的恐怖分子预测算法[J]. 计算机工程, 2020, 46(2): 315-320.
[7]	谢坤, 容钰添, 胡奉平, 陈桓, 姚小龙. 基于数据集成的随机森林算法[J]. 计算机工程, 2020, 46(12): 290-298.
[8]	张潘, 卢光跃, 吕少卿, 赵雪莉. 基于矩阵分解的属性网络表示学习[J]. 计算机工程, 2020, 46(10): 67-73.
[9]	刘佳美, 徐巧枝. 基于机器学习的SDN网络流量预测与部署策略[J]. 计算机工程, 2020, 46(10): 223-230.
[10]	王亮, 王敏, 王晓鹏, 罗威, 冯瑜. 基于流式计算的网络排队时延预测技术研究[J]. 计算机工程, 2020, 46(10): 289-293,300.
[11]	王重仁, 王雯, 佘杰, 凌晨. 融合深度神经网络的个人信用评估方法[J]. 计算机工程, 2020, 46(10): 308-314.
[12]	宋匡时, 李翀, 张士波. 一个轻量级分布式机器学习系统的设计与实现[J]. 计算机工程, 2020, 46(1): 201-207.
[13]	张景莲, 彭艳兵. 基于特征融合的恶意代码分类研究[J]. 计算机工程, 2019, 45(8): 281-286,295.
[14]	刘志昊, 孙晓山, 张阳. 基于改进PCFG的语言解释器模糊测试[J]. 计算机工程, 2019, 45(8): 22-24,30.
[15]	刘文杰, 江贺. 基于特征选择的软件缺陷报告严重性评估[J]. 计算机工程, 2019, 45(8): 80-85.

基于相关性的JPEG高压缩图像峰值信噪比盲估计

Blind Estimation of Peak Signal to Noise Ratio for JPEG Highly Compressed Images Based on Correlation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10