基于三维双流网络的视频目标移除篡改取证

doi:10.11959/j.issn.1000-436x.2021226

Abstract

Abstract:

In order to solve the problems of inaccurate temporal detection and location of the object removal tampered video， a video tamper forensics method based on 3D dual-stream network was proposed.Firstly， the spatial rich model （SRM） layer was used to extract the high-frequency information from video frames.Secondly， the improved 3D convolution （C3D） network was used as the feature extractor of the dual-stream network to extract the high-frequency information and low-frequency information from the high-frequency frame and the original video frame respectively.Finally， through compact bilinear pooling （CBP） layer， two sets of different feature vectors were fused into one set of feature vectors for classification prediction.The experimental results demonstrate that the classification accuracy of the proposed method in all video frames has an advantage in SYSU-OBJFORG dataset， which makes the temporal detection and location of object removal tampered video more accurate.

Key words: object removal tamper detection, video passive forensics, 3D convolution, dual-stream network, compact bi-linear pooling

CLC Number:

TP309

Lizhi XIONG, Mengqi CAO, Zhangjie FU. Forensic of video object removal tamper based on 3D dual-stream network[J]. Journal on Communications, 2021, 42(12): 202-211.

Figures/Tables 11

方法	PFACC	FFACC	FACC	Precision	Recall	F1值
文献[26]方法	98.45%	91.05%	96.79%	97.31%	91.05%	94.07%
文献[27]方法	99.42%	91.30%	97.60%	96.70%	91.30%	94.06%
文献[28]方法	99.47%	92.91%	98.19%	97.71%	92.91%	95.24%
文献[29]方法	99.50%	98.75%	99.34%	98.14%	98.75%	98.44%
本文方法	$99 . 86 %$	$99 . 18 %$	$99 . 52 %$	$99 . 86 %$	$99 . 18 %$	$99 . 51 %$

References 36

[1]	CHEN S D , TAN S Q , LI B ,et al. Automatic detection of object-based forgery in advanced video[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2016,26(11): 2138-2151.
[2]	冯春晖, 徐正全, 郑兴辉 ,等. 数字可视媒体取证[J]. 通信学报, 2014,35(4): 155-165.
	FENG C H , XU Z Q , ZHENG X H ,et al. Digital visual media forensics[J]. Journal on Communications, 2014,35(4): 155-165.
[3]	姚晔, 胡伟通, 任一支 ,等. 数字视频区域篡改的检测与定位[J]. 中国图象图形学报, 2018,23(6): 779-791.
	YAO Y , HU W T , REN Y Z ,et al. Detection and localization of digital video regional tampering[J]. Journal of Image and Graphics, 2018,23(6): 779-791.
[4]	ALORAINI M , SHARIFZADEH M , SCHONFELD D . Sequential and patch analyses for object removal video forgery detection and localization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020,31(3): 917-930.
[5]	DING X L , ZHU N B , LI L D ,et al. Robust localization of interpolated frames by motion-compensated frame interpolation based on an artifact indicated map and tchebichef moments[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019,29(7): 1893-1906.
[6]	DING X L , YANG G B , LI R ,et al. Identification of motion-compensated frame rate up-conversion based on residual signals[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018,28(7): 1497-1512.
[7]	LIAO X , YU Y B , LI B ,et al. A new payload partition strategy in color image steganography[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020,30(3): 685-696.
[8]	肖斌, 景如霞, 毕秀丽 ,等. 基于分组SIFT的图像复制粘贴篡改快速检测算法[J]. 通信学报, 2020,41(3): 62-70.
	XIAO B , JING R X , BI X L ,et al. Fast copy-move forgery detection algorithm based on group SIFT[J]. Journal on Communications, 2020,41(3): 62-70.
[9]	李岩, 刘念, 张斌 ,等. 图像镜像复制粘贴篡改检测中的 FI-SURF算法[J]. 通信学报, 2015,36(5): 58-69.
	LI Y , LIU N , ZHANG B ,et al. FI-SURF algorithm for image copy-flip-move forgery detection[J]. Journal on Communications, 2015,36(5): 58-69.
[10]	LIANG Z S , YANG G B , DING X L ,et al. An efficient forgery detection algorithm for object removal by exemplar-based image inpainting[J]. Journal of Visual Communication and Image Representation, 2015,30: 75-85.
[11]	ZHANG D Y , LIANG Z S , YANG G B ,et al. A robust forgery detection algorithm for object removal by exemplar-based image inpainting[J]. Multimedia Tools and Applications, 2018,77(10): 11823-11842.
[12]	ZHOU P , HAN X T , MORARIU V I ,et al. Learning rich features for image manipulation detection[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 1053-1061.
[13]	REN S Q , HE K M , GIRSHICK R ,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6): 1137-1149.
[14]	王珠珠 . 基于 U 型检测网络的图像篡改检测算法[J]. 通信学报, 2019,40(4): 171-178.
	WANG Z Z . Image forgery detection algorithm based on U-shaped detection network[J]. Journal on Communications, 2019,40(4): 171-178.
[15]	HSU C C , HUNG T Y , LIN C W ,et al. Video forgery detection using correlation of noise residue[C]// Proceedings of 2008 IEEE 10th Workshop on Multimedia Signal Processing. Piscataway:IEEE Press, 2008: 170-174.
[16]	WANG W H , FARID H . Exposing digital forgeries in interlaced and deinterlaced video[J]. IEEE Transactions on Information Forensics and Security, 2007,2(3): 438-449.
[17]	BESTAGINI P , MILANI S , TAGLIASACCHI M ,et al. Local tampering detection in video sequences[C]// Proceedings of 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP). Piscataway:IEEE Press, 2013: 488-493.
[18]	LIU Y Q , HUANG T Q , LIU Y F . A novel video forgery detection algorithm for blue screen compositing based on 3-stage foreground analysis and tracking[J]. Multimedia Tools and Applications, 2018,77(6): 7405-7427.
[19]	SITARA K , MEHTRE B M . Differentiating synthetic and optical zooming for passive video forgery detection:an anti-forensic perspective[J]. Digital Investigation, 2019,30: 1-11.
[20]	ZHANG J , SU Y T , ZHANG M Y . Exposing digital video forgery by ghost shadow artifact[C]// Proceedings of the First ACM workshop on Multimedia in forensics. New York:ACM Press, 2009: 49-54.
[21]	LI L D , WANG X W , ZHANG W ,et al. Detecting removed object from video with stationary background[C]// Digital Forensics and Watermaking. Berlin:Springer, 2013: 242-252.
[22]	ALORAINI M , SHARIFZADEH M , AGARWAL C ,et al. Statistical sequential analysis for object-based video forgery detection[J]. Electronic Imaging, 2019(5): 543-1.
[23]	ZHONG J L , PUN C M , GAN Y F . Dense moment feature index and best match algorithms for video copy-move forgery detection[J]. Information Sciences, 2020,537: 184-202.
[24]	CHEN R C , YANG G B , ZHU N B . Detection of object-based manipulation by the statistical features of object contour[J]. Forensic Science International, 2014,236: 164-169.
[25]	PANDEY R C , SINGH S K , SHUKLA K K . Passive copy-move forgery detection in videos[C]// Proceedings of 2014 International Conference on Computer and Communication Technology (ICCCT). Piscataway:IEEE Press, 2014: 301-306.
[26]	YAO Y , SHI Y Q , WENG S W ,et al. Deep learning for detection of object-based forgery in advanced video[J]. Symmetry, 2017,10(1): 3.
[27]	翁韶伟, 彭一航, 危博 ,等. 基于 Inception-V3 网络的双阶段数字视频篡改检测算法[J]. 广东工业大学学报, 2019,36(6): 16-23.
	WENG S W , PENG Y H , WEI B ,et al. A two-stage algorithm for video forgery detection based on inception-V3 network[J]. Journal of Guangdong University of Technology, 2019,36(6): 16-23.
[28]	陈临强, 杨全鑫, 袁理锋 ,等. 视频对象移除篡改的时空域定位被动取证[J]. 通信学报, 2020,41(7): 110-120.
	CHEN L Q , YANG Q X , YUAN L F ,et al. Passive forensic based on spatio-temporal localization of video object removal tampering[J]. Journal on Communications, 2020,41(7): 110-120.
[29]	YANG Q X , YU D J , ZHANG Z X ,et al. Spatiotemporal trident networks:detection and localization of object removal tampering in video passive forensics[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021,31(10): 4131-4144.
[30]	FRIDRICH J , KODOVSKY J . Rich models for steganalysis of digital images[J]. IEEE Transactions on Information Forensics and Security, 2012,7(3): 868-882.
[31]	MOLCHANOV P , YANG X D , GUPTA S ,et al. Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural networks[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2016: 4207-4215.
[32]	ZHANG P B , WANG X , ZHANG W H ,et al. Learning spatial-spectral-temporal EEG features with recurrent 3D convolutional neural networks for cross-task mental workload assessment[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019,27(1): 31-42.
[33]	WANG H H , WU X D , HUANG Z Y ,et al. High-frequency component helps explain the generalization of convolutional neural networks[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2020: 8681-8691.
[34]	LIN T Y , ROYCHOWDHURY A , MAJI S . Bilinear CNN models for fine-grained visual recognition[C]// Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2015: 1449-1457.
[35]	GAO Y , BEIJBOM O , ZHANG N ,et al. Compact bilinear pooling[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2016: 317-326.
[36]	TRAN D , BOURDEV L , FERGUS R ,et al. Learning spatiotemporal features with 3D convolutional networks[C]// Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2015: 4489-4497.

Metrics

Recommended 0

No Suggested Reading articles found!

方法	训练集/段	验证集/段	测试集/段	训练集遍历次数/次
文献[26]方法	40 （原始）+40 （篡改）	10 （原始）+10 （篡改）	50 （原始）+50 （篡改）	12 000
文献[27]方法	40 （原始）+40 （篡改）	10 （原始）+10 （篡改）	50 （原始）+50 （篡改）	40 000
文献[28]方法	50 （原始）+50 （篡改）	10 （原始）+10 （篡改）	40 （原始）+40 （篡改）	400
文献[29]方法	60 （原始）+60 （篡改）	20 （原始）+20 （篡改）	20 （原始）+20 （篡改）	400
本文方法	60 （原始）+60 （篡改）	20 （原始）+20 （篡改）	20 （原始）+20 （篡改）	28

Forensic of video object removal tamper based on 3D dual-stream network

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 36

Related Articles 1

Metrics

Recommended 0