您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2019, Vol. 49 ›› Issue (1): 23-29.doi: 10.6040/j.issn.1672-3961.0.2018.190

• 机器学习与数据挖掘 • 上一篇    下一篇

基于噪声水平估计的帧复制篡改取证算法

梅腊腊(),李然*(),邬长安   

  1. 信阳师范学院计算机与信息技术学院, 河南 信阳 464000
  • 收稿日期:2018-05-31 出版日期:2019-02-20 发布日期:2019-03-01
  • 通讯作者: 李然 E-mail:mll2106@163.com;liran358@163.com
  • 作者简介:梅腊腊(1991—)，女，河南信阳人，硕士研究生，主要研究方向为多媒体安全. E-mail:mll2106@163.com
  • 基金资助:
    信阳师范学院研究生科研创新基金(2017KYJJ47)

Detecting frame of repetition forgery based on noise level estimation

Lala MEI(),Ran LI*(),Chang'an WU   

  1. School of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, Henan, China
  • Received:2018-05-31 Online:2019-02-20 Published:2019-03-01
  • Contact: Ran LI E-mail:mll2106@163.com;liran358@163.com
  • Supported by:
    信阳师范学院研究生科研创新基金(2017KYJJ47)

RichHTML

14

PDF (PC)

360

摘要：

基于视频噪声的时域变化规律,提出一种可鉴别帧复制篡改的噪声水平检测方法。对各视频帧实施小波变换,利用小波系数的绝对中位差估计各视频帧中混入高斯噪声的标准差,并对标准差时域序列进行快速傅立叶变换,计算幅频谱的峰均比,再通过对峰均比作硬阈值判决,判断标准差时域序列是否存在周期性,自动识别帧复制篡改。结果表明,噪声水平检测方法可确保伪造视频幅频谱具有较大的峰均比,检测准确度比较高,相比于现有检测方法,避免噪声干扰带来的性能损失,表现出较好的检测性能。

关键词: 帧率提升, 帧复制, 视频取证, 噪声水平, 周期性检测

Abstract:

Detecting method of the varying noise level in temporal-domain was investigated based on noise-level, which could identify frame repetition (FR) forgery. Wavelet coefficients were computed for each video frame, and median absolute deviation (MAD) of wavelet coefficients was used to estimate the standard deviation of Gaussian noise mixed in each video frame. Fast Fourier transform (FFT) was used to calculate the amplitude spectrum of the standard deviation curve of the video sequence, and to provide the peak-mean ratio (PMR) of the amplitude spectrum. In order to automatically identify FR forgery, a hard threshold decision based on PMR was taken to determine whether the standard deviation had a periodicity in time domain. The experimental results showed that the proposed method ensured a large PMR for the forged video and high detection accuracy. The proposed method presented a better detection performance when compared with the existing detection, avoiding the performance loss from noise.

Key words: frame rate up-conversion, frame repetition, video forensics, noise level, periodicity detection

中图分类号: 

  • TN919.8

图1

帧复制篡改示例"

图2

噪声水平检测方法的流程图"

图3

原始与伪造Foreman视频序列的噪声标准差曲线"

图4

原始与伪造Foreman视频序列的噪声标准差幅频谱"

图5

原始与伪造视频序列的噪声标准差幅频谱"

表1

不同检测方法的平均幅频谱峰均比"

检测方法 QCIF CIF 720P 1080P 整体测试集
NS PS Δ NS PS Δ NS PS Δ NS PS Δ NS PS Δ
残差检测 6.76 17.24 0.61 7.67 19.88 0.61 10.04 29.58 0.66 11.73 23.88 0.51 8.63 21.98 0.61
相似性检测 7.36 21.91 0.66 7.63 24.31 0.69 10.17 29.63 0.66 11.90 26.30 0.55 8.79 25.23 0.65
噪声水平检测 2.42 27.32 0.91 2.45 30.17 0.92 2.93 28.32 0.89 2.92 27.95 0.889 2.62 28.85 0.91

表2

不同检测方法的FNR、FPR和DA值"

检测方法 QCIF CIF 720P 1080P 整体测试集
FNR FPR DA FNR FPR DA FNR FPR DA FNR FPR DA FNR FPR DA
残差检测 0.70 0.10 0.60 0.71 0 0.64 0.90 0 0.55 1.00 0 0.50 0.80 0.02 0.59
相似性检测 0.70 0 0.65 0.67 0 0.67 0.80 0 0.60 1.00 0 0.50 0.76 0 0.62
噪声水平检测 0 0 1.00 0 0 1.00 0 0 1.00 0.25 0 0.88 0.04 0 0.98
1 TSAI T H , SHI A T , HUANG K T . Accurate frame rate up-conversion for advanced visual quality[J]. IEEE Transactions on Broadcasting, 2016, 62 (2): 426- 435.
doi: 10.1109/TBC.2016.2550764
2 BAO W , ZHANG X , CHEN L , et al. High-order model and dynamic filtering for frame rate up-conversion[J]. IEEE Transactions on Image Processing, 2018, 27 (8): 3813- 3826.
doi: 10.1109/TIP.2018.2825100
3 LU G , ZHANG X , CHEN L , et al. Novel integration of frame rate up conversion and HEVC coding based on rate-distortion optimization[J]. IEEE Transactions on Image Processing, 2018, 27 (2): 678- 691.
doi: 10.1109/TIP.2017.2767782
4 BIAN S , LUO W , HUANG J . Exposing fake bit rate videos and estimating original bit rates[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2014, 24 (12): 2144- 2154.
5 BESTAGINI P, BATTAGLIA S, MILANI S, et al. Detection of temporal interpolation in video sequences[C]//International Conference on Acoustics, Speech and Signal Processing. Vancouver, Canada: IEEE, 2013: 3033-3037.
6 XIA M , YANG G , Li L , et al. Detecting video frame rate up-conversion based on frame-level analysis of average texture variation[J]. Multimedia Tools & Applications, 2016, 76 (6): 1- 23.
7 BIAN S , LUO W , HUANG J . Detecting video frame-rate up-conversion based on periodic properties of inter-frame similarity[J]. Multimedia Tools and Applications, 2014, 72 (1): 437- 451.
doi: 10.1007/s11042-013-1364-5
8 WANG Z , BOVIK A C , SHEIKH H R , et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transaction on Image Processing, 2004, 13 (4): 600- 611.
doi: 10.1109/TIP.2003.819861
9 YANG J , HUANG T , SU L . Using similarity analysis to detect frame duplication forgery in videos[J]. Multimedia Tools and Applications, 2016, 75 (4): 1- 19.
10 DING X , YANG G , LI R , et al. Identification of motion-compensated frame rate up-conversion based on residual signal[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2018, 28 (7): 1497- 1512.
11 SARWER M G , PO L M . Fast bit rate estimation for mode decision of H.264/AVC[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2007, 17 (10): 1402- 1407.
12 SULLIVANG J , OHM J , HAN W J , et al. Overview of the high efficiency video coding (HEVC) standard[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2012, 22 (12): 1649- 1668.
13 PAPOULIS A , PILLAI S U . Probability, random variables and stochastic processes[M]. New York: USA, McGraw-Hill, 2002.
14 BERGLAND G D . Fast Fourier transforms hardware implementations-a survey[J]. IEEE Transactions on Audio & Electroacoustics, 1969, 17 (2): 109- 119.
15 TAI S C, YANG S M. A fast method for image noise estimation using Laplacian operator and adaptive edge detection[C]//International Symposium on Communications Control and Signal Processing. St.Julians, Malta: IEEE, 2008: 1077-1081.
16 ZORAN D, WEISS Y. Scale invariance and noise in natural images[C]//International Conference on Computer Vision. Kyoto, Japan: IEEE, 2009: 2209-2216.
17 LEIGH A, WONG A, CLAUSI D A, et al. Comprehensive analysis on the effects of noise estimation strategies on image noise artifact suppression performance[C]//International Symposium on Multimedia. California, USA: IEEE, 2011: 97-104.
18 DONOHO D L . De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory, 1995, 41 (3): 613- 627.
doi: 10.1109/18.382009
[1] 孙金庆, 周风余, 杨阳, 唐相猛, 刘兆琦. 基于多硬件编码器协同的高效红外视频编码[J]. 山东大学学报(工学版), 2015, 45(4): 19-24.
[2] 赵毅,赵珑,张有志,齐志峰 . 一种新的基于FRR的OBS突发组装算法[J]. 山东大学学报(工学版), 2006, 36(1): 34-36 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 李士进,王声特,黄乐平. 基于正反向异质性的遥感图像变化检测[J]. 山东大学学报(工学版), 2018, 48(3): 1 -9 .
[2] 李杰 刘弘. 基于遗传算法的分形艺术图案生成方法[J]. 山东大学学报(工学版), 2008, 38(6): 33 -36 .
[3] 闫崇京 廖文和 郭宇 程筱胜. 基于多色图的BOM建模[J]. 山东大学学报(工学版), 2008, 38(6): 70 -75 .
[4] 焦培刚 周以齐 王喜仓. 自由表面流动的三维SPH数值仿真研究[J]. 山东大学学报(工学版), 2009, 39(6): 92 -96 .
[5] 胥晓东 刘燕 王威强 陈同蕾 刘琦. 压力容器的无量纲设计法及其应用(Ⅱ)[J]. 山东大学学报(工学版), 2009, 39(6): 101 -104 .
[6] 孟祥星1,于大洋2,韩学山2,赵建国3. 太阳辐射与负荷波动的相关性对光伏发电并网的影响[J]. 山东大学学报(工学版), 2010, 40(2): 126 -129 .
[7] 赵继增. 青岛胶州湾海底隧道涌水断层全断面帷幕注浆技术研究[J]. 山东大学学报(工学版), 2009, 39(6): 116 -120 .
[8] 宋德杰. 晶体生长参数的检测与优化[J]. 山东大学学报(工学版), 2009, 39(6): 154 -158 .
[9] 王建明 宫文军 高娜. 基于ALE法的磨料水射流加工数值模拟[J]. 山东大学学报(工学版), 2010, 40(1): 48 -52 .
[10] 林爱华 蒋晓芸 苗风明. 粒子入射双δ势垒时空间分数阶薛定谔方程的解[J]. 山东大学学报(工学版), 2010, 40(1): 139 -143 .
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发