基于差分直方图中尾部信息的平滑滤波检测算法

doi:10.11896/jsjkx.200900121

计算机科学 ›› 2021, Vol. 48 ›› Issue (11): 234-241.doi: 10.11896/jsjkx.200900121

• 计算机图形学&多媒体 • 上一篇下一篇

基于差分直方图中尾部信息的平滑滤波检测算法

淡州阳, 刘粉林, 巩道福

战略支援部队信息工程大学网络空间安全学院郑州450001

收稿日期:2020-09-15 修回日期:2021-01-11 出版日期:2021-11-15 发布日期:2021-11-10
通讯作者: 刘粉林(liufenlin@vip.sina.com)
作者简介:danzy116@163.com
基金资助:
国家自然科学基金(61772549,U1736214)

Smoothing Filter Detection Algorithm Based on Middle and Tail Information of Differential Histogram

DAN Zhou-yang, LIU Fen-lin, GONG Dao-fu

School of Cybersapce Security,Information Engineering University,Zhengzhou 450001,China

Received:2020-09-15 Revised:2021-01-11 Online:2021-11-15 Published:2021-11-10
About author:DAN Zhou-yang,born in 1996,postgraduate.His main research interests include information security and digital image forensics.
LIU Fen-lin,born in 1964,Ph.D,professor,Ph.D supervisor.His main research interests include digital image forensics and information hiding.
Supported by:
National Natural Science Foundation of China(61772549,U1736214).

摘要/Abstract

摘要： 平滑处理是数字图像去噪和产生模糊效果的重要手段,经常被用于美化润饰“伪造”图像,因此对各种平滑滤波实施检测是十分有必要的。针对常见的图像平滑处理,文中提出了一种新的基于差分直方图中尾部信息的平滑滤波检测算法。首先,针对待检测图像,基于不同差分步长和方向构建多个差分绝对值直方图;然后,提取直方图中差分值为0和1的出现频率,以及直方图尾部从大到小若干个差分值及其出现频率构建多维检测特征;最后,构建SVM分类器对图像实施检测。在图像库中实施了平滑处理检测以及区分不同平滑滤波的实验,实验结果表明,所提算法对3种常见的空域平滑滤波(中值滤波、均值滤波、高斯滤波)均有优异的检测性能。此外,该算法能够有效地将平滑滤波与锐化、缩放、压缩等其他数字图像操作进行区分,并且在JPEG压缩图像中具有鲁棒性。

关键词: 差分直方图, 平滑检测, 平滑滤波, 数字图像取证

Abstract: Smoothing is an important method for digital image denoising and blurring.It is often used to beautify and retouch “forged” images.Therefore,it is necessary to detect various smoothing filters.Aiming at the common image smoothing proces-sing,this paper proposes a new smoothing filter detection algorithm based on the tail information of differential histogram.Firstly,for the image to be detected,multiple difference absolute value histograms are constructed based on different difference step lengths and directions.Then,the occurrence frequency of the difference values of 0 and 1 in the histogram is extracted,and the several difference values from large to small at the tail of the histogram and their occurrence frequency are extracted to construct multi-dimensional detection feature.Finally,an SVM classifier is constructed to detect images.The experiments of smoothing detection and distinguishing different smoothing filters are carried out on the image library.The experimental results show that the proposed algorithm has excellent detection performance for three common spatial smoothing filters,including median filter,ave-rage filter and Gaussian filter.In addition,the algorithm can effectively distinguish smoothing filter from sharpening,scaling,compression and other digital image operations,and has robustness in JPEG compressed image.

Key words: Difference histogram, Digital image forensics, Smoothing detection, Smoothing filter

中图分类号:

TP391

淡州阳, 刘粉林, 巩道福. 基于差分直方图中尾部信息的平滑滤波检测算法[J]. 计算机科学, 2021, 48(11): 234-241. https://doi.org/10.11896/jsjkx.200900121

DAN Zhou-yang, LIU Fen-lin, GONG Dao-fu. Smoothing Filter Detection Algorithm Based on Middle and Tail Information of Differential Histogram[J]. Computer Science, 2021, 48(11): 234-241. https://doi.org/10.11896/jsjkx.200900121

参考文献

[1]BAI Z W,YI T T,ZHOU M L,et al.Face Image InpaintingMethod Based on Multi-Scale Feature Fusion[J].Computer Engineering,2021,47(5):213-220,228.
[2]BAISHYA N,BORA P.Luminance Channel Based CameraModel Identification[C]//2020 International Conference on Signal Processing and Communications (SPCOM).Bangalore:IEEE,2020:1-5.
[3]LI Y,ZHOU J.Fast and Effective Image Copy-Move ForgeryDetection via Hierarchical Feature Point Matching[J].IEEE Transactions on Information Forensics and Security,2019,14(5):1307-1322.
[4]XIAO B,WEI Y,BI X,et al.Image splicing forgery detectioncombining coarse to refined convolutional neural network and adaptive clustering[J].Information Sciences,2020,511:172-191.
[5]PANG R L,LIN J,ZHANG L.Grid-driven Bi-directional Image Stitching Algorithm[J].Computer Science,2020,47(3):130-136.
[6]BOROUMAND M,FRIDRICH J.Deep Learning for Detecting Processing History of Images[J].Electronic Imaging,2018,2018(7):213-1-213-9.
[7]WANG P,LIU F,YANG C.Thresholding binary codingfor image forensics of weak sharpening[J].Signal Processing Image Communication,2020,88:115956.
[8]ZHANG Q,LU W,HUANG T,et al.On the Robustness of JPEG Post-Compression to Resampling Factor Estimation[J].Signal Processing,2019,168:107371.
[9]LIU R H,XIE T.Image Decomposition Based on Improved Total Variation Method[J].Journal of Chongqing Technology and Business University:Natural Science Edition,2020,34(7):156-161.
[10]KIRCHNER M,FRIDRICH J.On detection of median filtering in digital images[C]//Media Forensics & Security II.San Jose:International Society for Optics and Photonics,2010:10-1-10-12.
[11]CAO G,ZHAO Y,NI R,et al.Forensic detection of median filtering in digital images[C]//IEEE International Conference on Multimedia & Expo.Singapore:IEEE,2010:89-94.
[12]BOVIK A.Streaking in median filtered images[J].IEEE Tran-sactions on Acoustics Speech and Signal Processing,1987,35(4):493-503.
[13]YUAN H.Blind Forensics of Median Filtering in Digital Images[J].IEEE Transactions on Information Forensics and Security,2011,6(4):1335-1345.
[14]CHEN C,NI J,HUANG J.Blind Detection of Median Filtering in Digital Images:A Difference Domain Based Approach[J].IEEE Transactions on Image Processing,2013,22(12):4699-4710.
[15]KANG X,STAMM M,PENG A,et al.Robust Median Filtering Forensics Using an Autoregressive Model[J].IEEE Transactions on Information Forensics and Security,2013,8(9):1456-1468.
[16]LAI Y,GAO T,LI J,et al.Forensic Detection of Median Filtering in Digital Images Using the Coefficient-Pair Histogram of DCT Value and LBP Pattern[C]//International Conference on Intelligent Computing.Cairo:Springer,2015:421-432.
[17]GAO H,GAO T,CHENG R.Robust detection of median filtering based on data-pair histogram feature and local configuration pattern[J].Journal of Information Security and Applications,2020,53:102506.
[18]DING F,SHI Y,ZHU G,et al.Smoothing identification for di-gital image forensics[J].Multimedia Tools and Applications,2019,78(7):8225-8245.
[19]LI M F,WANG C,PENG A J,et al.A Blind Forensics Algorithm for Digital Image Smoothing Filtering[J].Semiconductor Optoelectronics,2017,38(3):430-434.
[20]BAYAR B,STAMM M.Constrained Convolutional Neural Networks:A New Approach Towards General Purpose Image Manipulation Detection[J].IEEE Transactions on Information Forensics and Security,2018,13(11):2691-2706.
[21]YANG B,SUN X,CAO E,et al.Convolutional neural network for smooth filtering detection[J].IET Image Processing,2018,12(8):1432-1438.
[22]LIU A,ZHAO Z,ZHANG C,et al.Smooth filtering identifica-tion based on convolutional neural networks[J].Multimedia Tools and Applications,2019,78(19):26851-26865.
[23]WANG X L,LI X.Target Tracking Algorithm Based on Correlated Filters and Convolutional Neural Network[J].Journal of Chongqing Technology and Business University:Natural Science Edition,2020,37(1):19-24.
[24]ZENG J,TAN S,LI B,et al.Large-scale JPEG steganalysisusing hybrid deep-learning framework[J].IEEE Transactions on Information Forensics & Security,2016,13(5):1200-1214.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于差分直方图中尾部信息的平滑滤波检测算法

Smoothing Filter Detection Algorithm Based on Middle and Tail Information of Differential Histogram

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	邢文博, 杜志淳. 数字图像复制粘贴篡改取证 Digital Image Forensics for Copy and Paste Tampering 计算机科学, 2019, 46(6A): 380-384.
[2]	康晓兵,魏生民. 一种基于自适应闭值的图像伪造检测算法 Adaptive Threshold-based Detection Algorithm for Image Copy-move Forgery 计算机科学, 2011, 38(3): 295-299.
[3]	郑逢斌，支晶晶，高海亮，赖积保，潘伟. 一种高光谱图像条带噪声去除改进算法 Improved Destriping Algorithm of Hyperspectral Images 计算机科学, 2010, 37(5): 265-267.
[4]	. 基于非参数平滑的OFDM系统信道估计算法计算机科学, 2009, 36(6): 53-56.