融合多特征的视频帧间篡改检测算法

doi:10.11959/j.issn.2096-109x.2020007

Abstract

Abstract:

Traditional passive forensics of video inter-frame tampering often relies on single feature.Each of these features is usually suitable for certain types of videos,while has low detection accuracy for other videos.To combine the advantages of these features,a video inter-frame tampering detection algorithm that could fuse multi-features was proposed.The algorithm firstly classified the input video into one group based on its space information and time information values.Then it calculated the VQA features that represented the video inter-frame continuity.These features were sorted by the SVM-RFE feature recursive elimination algorithm.Finally,the sorted features were filtered and fused by the sequential forward selection algorithm and Adaboost binary classifier.Experimental results show that the proposed algorithm could achieve higher tampering detection accuracy.

Key words: video tamper detection, fusion algorithm, feature selection, Adaboost binary classification, video grouping

CLC Number:

TP393

Hui XIAO,Bin WENG,Tianqiang HUANG,Han PU,Zehui HUANG. Video inter-frame tampering detection algorithm fusing multiple features[J]. Chinese Journal of Network and Information Security, 2020, 6(1): 84-93.

Figures/Tables 8

References 37

[1]	INDEX C V N . Forecast and methodology,2016–2021[R]. White Paper,2017, 6.
[2]	IULIANI M , SHULLANI D , FONTANI M ,et al. A video forensic framework for the unsupervised analysis of MP4-like file container[J]. IEEE Transactions on Information Forensics and Security, 2018,14(3): 635-645.
[3]	AFCHAR D , NOZICK V , YAMAGISHI J ,et al. Mesonet:a compact facial video forgery detection network[C]// 2018 IEEE International Workshop on Information Forensics and Security (WIFS). 2018: 1-7.
[4]	MATERN F , RIESS C , STAMMINGER M . Exploiting visual artifacts to expose deepfakes and face manipulations[C]// 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW). 2019: 83-92.
[5]	SINGH R D , AGGARWAL N . Video content authentication techniques:a comprehensive survey[J]. Multimedia Systems, 2018,24(2): 211-240.
[6]	CHAO J , JIANG X , SUN T . A novel video inter-frame forgery model detection scheme based on optical flow consistency[C]// International Workshop on Digital Watermarking. 2012: 267-281.
[7]	WU Y , JIANG X , SUN T ,et al. Exposing video inter-frame forgery based on velocity field consistency[C]// 2014 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). 2014: 2674-2678.
[8]	LIU Y , HUANG T . Exposing video inter-frame forgery by Zernike opponent chromaticity moments and coarseness analysis[J]. Multimedia Systems, 2017,23(2): 223-238.
[9]	WANG W , FARID H . Exposing digital forgeries in video by detecting double MPEG compression[C]// The 8th Workshop on Multimedia and Security. 2006: 37-47.
[10]	AGHAMALEKI J A , BEHRAD A . Inter-frame video forgery detection and localization using intrinsic effects of double compression on quantization errors of video coding[J]. Signal Processing:Image Communication, 2016,47: 289-302.
[11]	LI F , HUANG T . Video copy-move forgery detection and localization based on structural similarity[C]// The 3rd International Conference on Multimedia Technology (ICMT 2013). 2014: 63-76.
[12]	张珍珍, 侯建军, 李赵红 ,等. 基于 MSSIM 商一致性的视频插帧和删帧篡改检测[J]. 北京邮电大学学报, 2015,38(4): 84-88.
	ZHANG Z Z , HOU J J , LI Z H ,et al. Video-farm insertion and deflection detection based on consistency of quotients of MSSIM[J]. Journal of Beijing University of Posts and Telecommunications, 2015,38(4): 84-88.
[13]	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.
[14]	WANG Z , SIMONCELLI E P , BOVIK A C . Multiscale structural similarity for image quality assessment[C]// The Thrity-Seventh Asilomar Conference on Signals,Systems ＆ Computers,2003. 2003, 2: 1398-1402.
[15]	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.
[16]	SHEIKH H R , BOVIK A C . Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006,15(2): 430-444.
[17]	WANG Z , BOVIK A C . A universal image quality index[J]. IEEE Signal Processing Letters, 2002,9(3): 81-84.
[18]	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.
[19]	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.
[20]	MANNOS J , SAKRISON D . The effects of a visual fidelity criterion of the encoding of images[J]. IEEE Transactions on Information Theory, 1974,20(4): 525-536.
[21]	ZHANG L , SHEN Y , LI H . VSI:a visual saliency-induced index for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2014,23(10): 4270-4281.
[22]	ZHANG L , ZHANG L , MOU X ,et al. FSIM:a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011,20(8): 2378-2386.
[23]	WANG Z , LI Q . Information content weighting for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2011,20(5): 1185-1198.
[24]	LIU A , LIN W , NARWARIA M . Image quality assessment based on gradient similarity[J]. IEEE Transactions on Image Processing, 2012,21(4): 1500-1512.
[25]	LARSON E C , CHANDLER D M . Most apparent distortion:full-reference image quality assessment and the role of strategy[J]. Journal of Electronic Imaging, 2010,19(1):011006.
[26]	ZHANG L , LI H . SR-SIM:a fast and high performance IQA index based on spectral residual[C]// 2012 19th IEEE International Conference on Image Processing. 2012: 1473-1476.
[27]	ZHANG L , ZHANG L , MOU X . RFSIM:a feature based image quality assessment metric using Riesz transforms[C]// 2010 IEEE International Conference on Image Processing. 2010: 321-324.
[28]	LIU T J , LIN W , KUO C C J . Image quality assessment using multi-method fusion[J]. IEEE Transactions on Image Processing, 2012,22(5): 1793-1807.
[29]	LIN J Y , LIU T J , WU E C H ,et al. A fusion-based video quality assessment (FVQA) index[C]// Signal and Information Processing Association Annual Summit and Conference (APSIPA),2014 Asia-Pacific. 2014: 1-5.
[30]	HUANG T , ZHANG X , HUANG W ,et al. A multi-channel approach through fusion of audio for detecting video inter-frame forgery[J]. Computers ＆ Security, 2018,77: 412-426.
[31]	SHANABLEH T . Detection of frame deletion for digital video forensics[J]. Digital Investigation, 2013,10(4): 350-360.
[32]	LIU T J , LIN W , KUO C C J . Image quality assessment using multi-method fusion[J]. IEEE Transactions on Image Processing, 2012,22(5): 1793-1807.
[33]	INSTALLATIONS T , LINE L . Subjective video quality assessment methods for multimedia applications[J]. Networks, 1999,910(37):5.
[34]	GUYON I , WESTON J , BARNHILL S ,et al. Gene selection for cancer classification using support vector machines[J]. Machine Learning, 2002,46(1-3): 389-422.
[35]	HU Y J , SALMAN A H , WANG Y F ,et al. Construction and evaluation of video forgery detection database[J]. Journal of South China University of Technology (Natural Science), 2017,45(12): 57-64.
[36]	QADIR G , YAHAYA S , HO A T . Surrey university library for forensic analysis (SULFA) of video content[C]// IET Conference on Image Processing. 2012: 1-6.
[37]	PEDREGOSA F , VAROQUAUX G , GRAMFORT A ,et al. Scikit-learn:machine learning in Python[J]. Journal of Machine Learning Research, 2011,12: 2825-2830.

Metrics

Recommended 0

No Suggested Reading articles found!

指标索引	简称	中文全称	英文全称
m1	MSE	均方误差	mean-square error
m2	PSNR	峰值信噪比	peak singal-to-noise ratio
m3	SSIM	结构相似性	structural similarity index
m4	MSSIM	多尺度结构相似性	multiscale-SSIM
m5	VSNR	视觉信噪比	visual signal-to-noise-ratio
m6	VIF	视觉信息保真度	visual information fidelity
m7	VIFP	基于像素的视觉信息保真度	pixel-based VIF
m8	UQI	全局质量指标	universal quality index
m9	IFC	信息保真度测量	information fidelity criterion
m10	NQM	噪声质量检测	noise quality measure
m11	WSNR	加权信噪比	weighted signal-to-noise ratio
m12	SNR	信噪比	signal-to-noise ratio
m13	VSI	视觉显著索引	a visual saliency induced index
m14	FSIM	特征相似性	feature-similarity
m15	IWSSIM	信息内容加权的结构相似性	information content weighted SSIM
m16	GSM	梯度相似性度量	gradient similarity based metric
m17	MAD	最显著失真	most apparent distortion
m18	SRSIM	频谱残差相似度	spectral residual based similarity
m19	RFSIM	基于Riesz变换的特征相似度	Riesz transforms based feature similarity

神经网络	决策树	K最近邻	逻辑回归	朴素贝叶斯	随机森林	支持向量机	AdaBoost
0.862 465	0.724 582	0.868 036	0.885 097	0.862 465	0.823 12	0.868 036	0.903 552

索引	选入特征	融合框架得分
1	m9	0.958 257
2	m9、m12	0.902 498
3	m9、m12、m2	0.962 523
4	m9、m12、m2、m11	0.983 242
5	m9、m12、m2、m11、m1	0.971 359
6	m9、m12、m2、m11、m1、m5	0.971 054
7	m9、m12、m2、m11、m1、m5、m10	0.970 75
8	m9、m12、m2、m11、m1、m5、m10、m17	0.972 273
9	m9、m12、m2、m11、m1、m5、m10、m17、m19	0.969 226
10	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16	0.968 007
11	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18	0.969 835
12	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8	0.972 273
13	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13	0.969 835
14	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13、m4	0.972 882
15	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13、m4、m14	0.973 187
16	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13、m4、m14、m3	0.974 711
17	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13、m4、m14、m3、m6	0.966 789
18	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13、m4、m14、m3、m6、m7	0.966 484
19	m9、m12、m2、m11、m1、m5、m10、m17、m19、m16、m18、m8、m13、m4、m14、m3、m6、m7、m15	0.970 445
20	m9、m16、m6、m7、m15	0.971 054

方法名称	VFDD库中方法的得分	SULFA库中方法的得分
MSE	0.685 269	0.564 72
PSNR	0.685 215	0.566 762
SSIM	0.702 852	0.582 687
MSSIM	0.687 145	0.613 312
VSNR	0.667 632	0.666 803
VIF	0.800 633	0.543 079
VIFP	0.799 614	0.460 188
UQI	0.777 796	0.517 762
IFC	0.918 623	0.481 829
NQM	0.685 751	0.574 929
WSNR	0.693 149	0.508 371
SNR	0.693 256	0.477 746
VSI	0.651 71	0.490 813
FSIM	0.670 687	0.597 795
IWSSIM	0.663 611	0.625 153
GSM	0.689 182	0.599 428
MAD	0.749 518	0.644 753
SRSIM	0.751 581	0.571 254
RFSIM	0.726 493	0.601 062
MMF（无分组）	0.928 602	0.676 194
MMF（分组后）	0.929 236	0.794 227

Video inter-frame tampering detection algorithm fusing multiple features

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 37

Related Articles 5

Metrics

Recommended 0

[1]	Cong YI, Jun HU. Novel continuous identity authentication method based on mouse behavior [J]. Chinese Journal of Network and Information Security, 2022, 8(5): 179-188.
[2]	Xi FU,Hui LI,Xingwen ZHAO. Survey on phishing detection research [J]. Chinese Journal of Network and Information Security, 2020, 6(5): 1-10.
[3]	Fan CHAO,Zhi YANG,Xuehui DU,Yan SUN. Android malware detection method based on deep neural network [J]. Chinese Journal of Network and Information Security, 2020, 6(5): 67-79.
[4]	You YU, Yu FU, Xiaoping WU. Summary of text classification methods [J]. Chinese Journal of Network and Information Security, 2019, 5(5): 1-8.
[5]	Tie-ming CHEN,Xiao-hao WANG,Wei-wei PANG,Jie JIANG. Time series and semantics-based chinese microblog topic detection and tracking method [J]. Chinese Journal of Network and Information Security, 2016, 2(5): 21-29.