采用量化离散余弦变换系数检测视频单帧连续多次复制粘贴篡改

doi:10.11772/j.issn.1001-9081.2016.05.1356

计算机应用 ›› 2016, Vol. 36 ›› Issue (5): 1356-1361.DOI: 10.11772/j.issn.1001-9081.2016.05.1356

采用量化离散余弦变换系数检测视频单帧连续多次复制粘贴篡改

林晶^1,2, 黄添强^3,4, 赖玥聪^1,2, 卢贺楠^1,2

1. 福建师范大学数学与计算机科学学院, 福州 350007;
2. 福建师范大学网络安全与密码技术福建省高校重点实验室, 福州 350007;
3. 福建师范大学软件学院, 福州 350007;
4. 福建师范大学大数据分析与应用福建省高校工程研究中心, 福州 350007

收稿日期:2015-12-01 修回日期:2015-12-18 出版日期:2016-05-10 发布日期:2016-05-09
通讯作者: 黄添强
作者简介:林晶(1992-),女,福建莆田人,硕士研究生,主要研究方向:数据挖掘、视频篡改检测;黄添强(1971-),男,福建莆田人,教授,博士,主要研究方向:机器学习、数据挖掘、多媒体篡改检测;赖玥聪(1991-),男,江西赣州人,硕士研究生,主要研究方向:图像篡改检测、数据挖掘;卢贺楠(1988-),男,安徽霍邱人,硕士研究生,主要研究方向:机器学习、视频篡改检测。
基金资助:
国家自然科学基金资助项目(61070062);福建省高校产学合作科技重大项目(2015H6007);福州市科技计划项目(2014-G-76);福建省高等学校新世纪优秀人才支持计划项目(JA Il038);福建省科学厅K类基金资助项目(JK 2011007);福建省教育厅A类基金资助项目(JA10064);福建师范大学研究生教育改革研究项目(MY201414)。

Detection of continuously and repeated copy-move forgery to single frame in videos by quantized DCT coefficients

LIN Jing^1,2, HUANG Tianqiang^3,4, LAI Yueicong^1,2, LU Henan^1,2

1. School of Mathematics and Computer Science, Fujian Normal University, Fuzhou Fujian 350007, China;
2. Fujian Provincial University Key Laboratory of Network Security and Cryptography, Fujian Normal University, Fuzhou Fujian 350007, China;
3. Faculty of Software, Fujian Normal University, Fuzhou Fujian 350007, China;
4. Fujian Provincial University Engineering Research Center of Big Data Analysis and Application, Fujian Normal University, Fuzhou Fujian 350007, China

Received:2015-12-01 Revised:2015-12-18 Online:2016-05-10 Published:2016-05-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61070062), Industry-University Cooperation Major Projects in Fujian Province (2015H6007), Science and Technology Program of Fuzhou City (2014-G-76), Program for New Century Excellent Talents of University in Fujian Province (JAI1038), the K-class Foundation Project Science and Technology Department of Fujian (JK2011007), the A-class Foundation Project of Education Department of Fujian (JA10064), the Graduate Education Reform Research Project of Fujian Normal University (MY201414).

摘要/Abstract

摘要： 目前大多数时域视频帧复制粘贴篡改检测算法都是针对至少20帧以上的视频子序列的复制粘贴篡改,而对单帧复制粘贴篡改无法判断。而根据人眼视觉感知的特性,修改视频内容需要至少15帧以上的帧操作,因此篡改帧想通过单帧复制粘贴篡改来达到想要的效果,必须进行连续多次粘贴操作。为了检测这种篡改方式,针对性地提出了一种基于量化离散余弦变换(DCT)系数的视频单帧连续多次复制-粘贴篡改检测算法。首先,将视频转换为图像,采用量化后的DCT系数作为视频帧图像特征向量,并通过计算巴氏(Bhattacharyya)系数来衡量两相邻帧帧间相似度;再设定阈值来判断两相邻帧帧间相似度是否有异常,最后根据出现相似度异常的帧是否连续,以及连续出现的帧数来判断视频是否经过篡改,并定位篡改位置。实验结果表明,所提算法对不同场景的视频都能检测,不仅检测速度快,而且不受再压缩因素影响,算法的正确率高、漏检率低。

关键词: 视频篡改检测, 单帧复制粘贴, 离散余弦变换, 帧间相似度, Bhattacharyya系数

Abstract: Most existing detection algorithms of video frame copy-move forgery in time domain were designed for the copy-move forgery of video sequence containing 20 frames at least, and are difficult to detect single frame forgery. While according to the characteristics of human visual perception, 15 frames at least were needed to modify the video meaning. So when goal in vision was made by the tampering, continuous operation and many times were needed. In order to detect the tampering, a detection algorithm based on quantized Discrete Cosine Transform (DCT) coefficients for continuous and repeated single frame copy-move forgery in videos was proposed. Firstly, the video was converted into images, and quantized DCT coefficients were taken as the feature vector of a frame image. Then, the similarity between frames was measured by calculating Bhattacharyya coefficient, and threshold was set to judge the abnormal similarity between two adjacent frames. Finally, whether the video was tampered and the tampered positions were determined by the continuity of frames with abnormal similarity and the number of continuous frames. The experimental results show that the proposed algorithm can detect the video with different scenarios, it possesses fast detection speed, and is not affected by further compression factors, but also is of high accuracy and low omission ratio.

Key words: video tampering detection, single frame copy-move, Discrete Cosine Transform (DCT), intra-frame similarity, Bhattacharyya coefficient

中图分类号:

TP391

林晶, 黄添强, 赖玥聪, 卢贺楠. 采用量化离散余弦变换系数检测视频单帧连续多次复制粘贴篡改[J]. 计算机应用, 2016, 36(5): 1356-1361.

LIN Jing, HUANG Tianqiang, LAI Yueicong, LU Henan. Detection of continuously and repeated copy-move forgery to single frame in videos by quantized DCT coefficients[J]. Journal of Computer Applications, 2016, 36(5): 1356-1361.

参考文献

[1] 陈威兵, 杨高波, 陈日超, 等. 数字视频真实性和来源的被动取证[J].通信学报, 2011, 32(6):177-183. (CHEN W B, YANG G B, CHEN R C, et al. Digital video passive forensics for its authenticity and source[J].Journal on Communications, 2011, 32(6):177-182.)
[2] 周琳娜, 王东明. 数字图像取证技术[M]. 北京:北京邮电大学出版社, 2008:1-2. (ZHOU L N, WANG D M. Digital Image Forensics[M]. Beijing:Beijing University of Posts and Telecommunications Press, 2008:1-2.)
[3] WANG W, FARID H. Exposing digital forgeries in video by detecting double quantization[C]//Proceedings of the 11th ACM Workshop on Multimedia and Security. New York:ACM, 2009:39-48.
[4] ZHANG J, SU Y, ZHANG M. Exposing digital video forgery by ghost shadow artifact[C]//Proceedings of the 1st ACM Workshop on Multimedia in Forensics. New York:ACM, 2009:49-54.
[5] DELP E, MEMON N, WU M. Digital forensics[J]. IEEE Signal Processing Magazine, 2009, 26(2):14-15.
[6] MILANI S, FONTANI M, BESTAGINI P, et al. An overview on video forensics[J]. APSIPA Transactions on Signal and Information Processing, 2012, 1(1):1-18.
[7] DONG Q, YANG G, ZHU N. A MCEA based passive forensics scheme for detecting frame-based video tampering[J]. Digital Investigation, 2012, 9(2):151-159.
[8] WANG W, FARID H. Exposing digital forgeries in video by detecting duplication[C]//Proceedings of the 9th ACM Workshop on Multimedia and Security. New York:ACM, 2007:35-42.
[9] LIN G-S, CHANG J-F. Detection of frame duplication forgery in videos based on spatial and temporal analysis[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2012, 26(7):21250017.
[10] LI F, HUANG T. Video copy-move forgery detection and localization based on structural similarity[C]//Proceedings of the 3rd International Conference on Multimedia Technology. Berlin:Springer, 2014:63-76.
[11] ZHAO J, GUO J. Passive forensics for copy-move image forgery using a method based on DCT and SVD[J]. Forensic Science International, 2013, 233(1):158-166.
[12] CHOI E, LEE C. Feature extraction based on the Bhattacharyya distance[J]. Pattern Recognition, 2003, 36(8):1703-1709.
[13] QADIR G, YAHAYA S, HO A T. Surrey University Library for Forensic Analysis (SULFA) of video content[C]//Proceedings of the 2012 IET Conference on Image Processing. London:IET Press, 2012:1-6.

[1]	高彦彦, 李莉, 张晶, 贾英茜. 结合梯度投影稀疏重构和复数小波的图像重构[J]. 计算机应用, 2020, 40(2): 486-490.
[2]	陈善学, 漆若兰, 唐义嫄. 基于多变换域的彩色图像多功能水印算法[J]. 计算机应用, 2018, 38(8): 2274-2279.
[3]	李晨, 王可鑫, 田丽华. 基于声道低频能量比的MP3压缩域音频水印算法[J]. 计算机应用, 2018, 38(8): 2301-2305.
[4]	尹立, 林新棋, 陈黎飞. 视频帧内运动目标移除篡改检测算法[J]. 计算机应用, 2018, 38(3): 879-883.
[5]	张春艳, 李京兵, 王双双. 基于离散小波变换和感知哈希的加密医学图像检索算法[J]. 计算机应用, 2018, 38(2): 539-544.
[6]	任帅, 索丽, 张弢, 杨涛, 慕德俊. 基于3D高效率视频编码背景的信息隐藏算法[J]. 计算机应用, 2017, 37(6): 1616-1619.
[7]	熊浩, 任延珍, 王丽娜. 面向高级音频编码的通用隐写分析方法[J]. 计算机应用, 2016, 36(2): 382-386.
[8]	谢斌, 乐鸿浩, 陈博. 基于小波去噪与离散余弦变换相结合的正交频分复用系统信道估计算法[J]. 计算机应用, 2015, 35(9): 2461-2464.
[9]	刘立冬田翔. 基于H.264压缩域的视频盲水印算法[J]. 计算机应用, 2013, 33(07): 1866-1869.
[10]	陈善学冯银波. 基于四元数模型和奇异值分解的图像水印算法[J]. 计算机应用, 2013, 33(06): 1626-1629.
[11]	胡然张天骐高洪兴. 基于离散小波变换和离散余弦变换域的扩频水印盲提取算法[J]. 计算机应用, 2013, 33(01): 138-141.
[12]	段继忠张立毅刘昱孙云山. 基于压缩感知的改进MPEG-2编码方案[J]. 计算机应用, 2012, 32(12): 3411-3414.
[13]	李朝友孙济洲. 基于区域收缩的大规模数据库人脸识别[J]. 计算机应用, 2012, 32(07): 2049-2052.
[14]	李睿何坤周激流. 基于图像变换系数稀疏性的去噪处理[J]. 计算机应用, 2011, 31(11): 3015-3017.
[15]	曲巨宝林宏基. 基于特征点密度的DCT域盲检测数字水印算法[J]. 计算机应用, 2011, 31(10): 2670-2673.

采用量化离散余弦变换系数检测视频单帧连续多次复制粘贴篡改

Detection of continuously and repeated copy-move forgery to single frame in videos by quantized DCT coefficients

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics