A multi-channel approach through fusion of audio for detecting video inter-frame forgery

被引：11
作者：
Huang, Tianqiang [1 ,2 ,3 ]
Zhang, Xueli [1 ,2 ,3 ]
Huang, Wei [1 ,2 ,3 ]
Lin, Lingpeng [1 ,2 ,3 ]
Su, Weifeng [4 ]
机构：
[1] Fujian Normal Univ, Coll Math & Informat, Fuzhou 350007, Fujian, Peoples R China
[2] Fujian Digital Inst Big Data Secur Technol, Fuzhou 350007, Fujian, Peoples R China
[3] Fujian Prov Engn Res Ctr Big Data Anal & Applicat, Fuzhou 350007, Fujian, Peoples R China
[4] BNU HKBU United Int Coll, Zhuhai 519000, Peoples R China
来源：
COMPUTERS & SECURITY | 2018年 / 77卷
基金：
中国国家自然科学基金;
关键词：
Video forensics; Frame insertion and deletion forgeries; Copy-move forgery; Wavelet singularity analysis; Perceptual hashing; Quaternion discrete cosine transform (QDCT);
D O I：
10.1016/j.cose.2018.04.013
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The forgery operation of digital video in the temporal domain is often accompanied by the synchronization of the audio channel operation. In this paper, we proposed a fusion of audio forensics detection methods for video inter-frame forgery. First, the audio channel of the video is extracted, and discrete wavelet packet decomposition and analysis of singularity points of audio signals are used to locate the forged singularity points. Next, features of each frame of the video are extracted with the perceptual hash and used to calculate the similarity between consecutive frames, to locate the forgery position in the video frame sequence. We fused the results of the audio channel and the video frame sequence channel. The QDCT feature is used to further fine detect the suspected forgery location. Our method can position replication source locations for copy-move forgery. Experiments show that our method has higher accuracy and better performance in comparison with similar methods, especially on the delete forgery operation. (C) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码：412 / 426
页数：15
相关论文
共 14 条
  • [1] Chao J., 2013, INT WORKSH DIG WAT, P267, DOI DOI 10.1007/978-3-642-40099-5_22
  • [2] Detecting and locating digital audio forgeries based on singularity analysis with wavelet packet
    Chen, Jiaorong
    Xiang, Shijun
    Huang, Hongbin
    Liu, Weiping
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 75 (04) : 2303 - 2325
  • [3] Feature extraction based on the Bhattacharyya distance
    Choi, E
    Lee, C
    [J]. PATTERN RECOGNITION, 2003, 36 (08) : 1703 - 1709
  • [4] Feng C, 2014, P 2 ACM WORKSH INF H, P171, DOI DOI 10.1145/2600918.2600923
  • [5] Quaternion discrete cosine transform and its application in color template matching
    Feng, Wei
    Hu, Bo
    [J]. CISP 2008: FIRST INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOL 2, PROCEEDINGS, 2008, : 252 - 256
  • [6] Gironi A., 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), P6226, DOI 10.1109/ICASSP.2014.6854801
  • [7] [黄添强 Huang Tianqiang], 2011, [南京大学学报. 自然科学版, Journal of Nanjing University], V47, P493
  • [8] Image splicing detection based on Markov features in QDCT domain
    Li, Ce
    Ma, Qiang
    Xiao, Limei
    Li, Ming
    Zhang, Aihua
    [J]. NEUROCOMPUTING, 2017, 228 : 29 - 36
  • [9] Temporal Forensics and Anti-Forensics for Motion Compensated Video
    Stamm, Matthew C.
    Lin, W. Sabrina
    Liu, K. J. Ray
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2012, 7 (04) : 1315 - 1329
  • [10] Wang WH, 2009, MM&SEC'09: PROCEEDINGS OF THE 2009 ACM SIGMM MULTIMEDIA AND SECURITY WORKSHOP, P39
12