广东工业大学学报 ›› 2019, Vol. 36 ›› Issue (06): 16-23.doi: 10.12052/gdutxb.190046

• 综合研究 • 上一篇    下一篇

基于Inception-V3网络的双阶段数字视频篡改检测算法

翁韶伟1,2, 彭一航1,2, 危博1, 易林1, 叶武剑1   

  1. 1. 广东工业大学 信息工程学院, 广东 广州 510006;
    2. 广东省智能信息重点实验室, 广东 深圳 518060
  • 收稿日期:2019-03-25 出版日期:2019-11-28 发布日期:2019-11-01
  • 通信作者: 易林(1992-),男,硕士研究生,主要研究方向为深度学习和多媒体数字取证等,E-mail:90583068@qq.com E-mail:90583068@qq.com
  • 作者简介:翁韶伟(1980-),女,副教授,博士,主要研究方向为图像可逆水印、信息隐藏和视频篡改等。
  • 基金资助:
    国家自然科学基金资助项目（61872095，61872128，61571139，61201393）；广东省智能信息处理重点实验室、深圳市媒体信息内容安全重点实验室2018年开放基金课题（ML-2018-03）；广东省信息安全技术重点实验室开放课题基金资助（2017B030314131）；广州市珠江科技新星专题（2014J2200085）

A Two-stage Algorithm for Video Forgery Detection Based on Inception-V3 Network

Weng Shao-wei1,2, Peng Yi-hang1,2, Wei Bo1, Yi Lin1, Ye Wu-jian1   

  1. 1. School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China;
    2. Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen 518060, China
  • Received:2019-03-25 Online:2019-11-28 Published:2019-11-01

HTML

PDF (PC)

2734

摘要： 为了克服现有数字视频取证算法识别准确率低、定位能力差等缺点，提出一种具有高识别率且定位准确的基于Inception-V3网络的二级分类取证算法.在第一级分类器中提出简单的阈值判断方法来区分原始和篡改视频，第二级分类器将采用Inception-V3网络的稠密卷积核结构来自动提取篡改视频帧的高维多尺度特征.高维多尺度特征有助于提升篡改视频帧的识别率.实验结果表明，本文提出的算法不仅能准确地检测出篡改视频，还能从篡改视频中精确定位出篡改帧.

关键词: 数字视频取证, 视频篡改识别, Inception-V3网络, 篡改帧定位

Abstract: In order to overcome the shortcomings (e.g. low recognition accuracy and poor localization ability) of existing video forensics techniques, a two-stage algorithm is proposed based on Inception-V3 network, whose advantage lies in the fact that it can accurately identify a forged video and locate its forged frames. After an extensive research, it is found that the average value of all the pixels in a pristine video sequence is always larger than its forged one after the video sequence is processed via several operations such as high-pass filtering and convolution. To this end, in the first stage, a simple algorithm is proposed in which a predefined threshold is employed to distinguish a forged video and a pristine video. Considering the fact that features of each frame need to be extracted manually in existing algorithms, the dense convolution kernel structure of Inception-V3 network is adopted in the second stage to automatically extract high dimensional and multi-scale features of each forged frame. Inception-V3 network can accurately locate forged frames in a forged video since dimensional and multi-scale features can more adequately express the input information. The experiments show that the proposed method performs very well both in forged video identification and forged frame localization.

Key words: digital video forensics, video forgery detection, Inception-V3 network, forged frame localization

中图分类号: 

  • TP391
[1] NA S, OH W, JEONG D. A frame-based video signature method for very quick video identification and location[J]. ETRI Journal, 2013, 35(2):281-291
[2] LEE S, YOO C D. Robust video fingerprinting for content-based video identification[J]. IEEE Trans on Circuits and Systems for Video Technology, 2008, 18(7):983-988
[3] CHETTY G, BISWAS M, SIGNH R. Digital video tamper detection based on multimodal fusion of residue features[C]//Fourth International Conference on Network & System Security. IEEE Computer Society. Melbourne:IEEE, 2010:606-613.
[4] GOODWIN J, CHETTY G. Blind video tamper detection based on fusion of source features[C]//International Conference on Digital Image Computing:Techniques & Applications. Noosa:IEEE, 2011:608-613.
[5] BESTAGINI P, MILANI S, TAGLIASACCHI M, et al. Local tampering detection in video sequences[C]//Proceedings of the IEEE 15th International Workshop on Multimedia Signal Processing. Pula:IEEE, 2013:488-493.
[6] LI L, WANG X, ZHANG W, et al. Detecting removed object from video with stationary background[C]//International Conference on Digital Forensics & Watermarking. Shanghai:Springer, 2012:242-252.
[7] BIDOKHTI A, CHAEMMAGHAMI S. Detection of region copy move forgery in MPEG videos using optical flow[C]//International Symposium on Artificial Intelligence and Signal Processing. Mashhad:IEEE, 2015:13-17.
[8] PANDEY R C, SINGH S K, SHUKLA K K. Passive copy-move forgery detection in videos[C]//Proceedings of the International Conference on Computer and Communication Technology. Allahabad:Springer, 2014:301-306.
[9] 叶武剑, 高海健, 翁韶伟, 等. 基于CGAN网络的二阶段式艺术字体渲染方法[J]. 广东工业大学学报, 2019, 36(3):48-54 YE W J, GAO H J, WENG S W, et al. A Two-stage effect rendering method for art font based on CGAN network[J]. Journal of Guangdong University of Technology, 2019, 36(3):48-54
[10] CHEN S, TAN S, LI B, et al. Automatic detection of object-based forgery in advanced video[J]. IEEE Trans on Circuits and Systems for Video Technology, 2016, 26(11):2318-2350
[11] YAO Y, SHI Y, WENG S, et al. Deep learning for detection of object-based forgery in advanced video[J]. Symmetry, 2017, 10(3):1-10
[12] 刘绍辉, 韩露, 姚鸿勋. 抗共谋攻击的视频水印算法[J]. 通信学报, 2010, 31(1):14-19 LIU S H, HAN L, YAO H X. Video watermarking algorithm for resisting collusion attacks[J]. Journal on Communications, 2010, 31(1):14-19
[13] CHRISTIAN S, VICENT V, LOFFE S, et al. Rethinking the inception architecture for computer vision[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE, 2016:2818-2826.
[1] 谢国波, 林立, 林志毅, 贺笛轩, 文刚. 基于YOLOv4-MP的绝缘子爆裂缺陷检测方法[J]. 广东工业大学学报, 2023, 40(02): 15-21.
[2] 陈靖宇, 吕毅. 基于脉冲神经网络的冷链制冷机结霜检测方法[J]. 广东工业大学学报, 2023, 40(01): 29-38.
[3] 叶文权, 李斯, 凌捷. 基于多级残差U-Net的稀疏SPECT图像重建[J]. 广东工业大学学报, 2023, 40(01): 61-67.
[4] 邹恒, 高军礼, 张树文, 宋海涛. 围棋机器人落子指引装置的设计与实现[J]. 广东工业大学学报, 2023, 40(01): 77-82,91.
[5] 谢光强, 许浩然, 李杨, 陈广福. 基于多智能体强化学习的社交网络舆情增强一致性方法[J]. 广东工业大学学报, 2022, 39(06): 36-43.
[6] 刘信宏, 苏成悦, 陈静, 徐胜, 罗文骏, 李艺洪, 刘拔. 高分辨率桥梁裂缝图像实时检测[J]. 广东工业大学学报, 2022, 39(06): 73-79.
[7] 熊武, 刘义. 粒子滤波算法在BDS高铁铁轨静态形变监测中的应用研究[J]. 广东工业大学学报, 2022, 39(04): 66-72.
[8] 易闽琦, 刘洪伟, 高鸿铭. 电商平台产品共同购买网络的影响因素研究[J]. 广东工业大学学报, 2022, 39(03): 16-24.
[9] 丘展春, 费伦科, 滕少华, 张巍. 余弦相似度保持的掌纹识别算法[J]. 广东工业大学学报, 2022, 39(03): 55-62.
[10] 郑佳碧, 杨振国, 刘文印. 基于细粒度混杂平衡的营销效果评估方法[J]. 广东工业大学学报, 2022, 39(02): 55-61.
[11] Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[12] 李光程, 赵庆林, 谢侃. 去中心化的数据处理方案设计[J]. 广东工业大学学报, 2021, 38(06): 77-83.
[13] 谢光强, 赵俊伟, 李杨, 许浩然. 基于多集群系统的车辆协同换道控制[J]. 广东工业大学学报, 2021, 38(05): 1-9.
[14] 张巍, 张圳彬. 联合图嵌入与特征加权的无监督特征选择[J]. 广东工业大学学报, 2021, 38(05): 16-23.
[15] 邓杰航, 袁仲鸣, 林好润, 顾国生. 协同超像素和视觉显著性的图像质量评价[J]. 广东工业大学学报, 2021, 38(05): 33-39.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发