Please wait a minute...
浙江大学学报(工学版)
自动化技术、电信工程     
基于JPEG系数变化率的图像复制粘贴篡改检测
赵洁1,2, 郭继昌1
1. 天津大学 电子信息工程学院,天津 300072;2. 天津城建大学 计算机与信息工程学院,天津 300384
Image copy paste forgery detection based on JPEG coefficients change rate
ZHAO Jie1,2, GUO Ji chang1
1. School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China; 2. School of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, China
 全文: PDF(2693 KB)   HTML
摘要:
针对JPEG图像的复制粘贴篡改方式,提出单一流程的被动检测方法,实现了同幅图像复制粘贴篡改和异幅图像合成篡改的检测定位.该算法判断篡改图像是否为JPEG格式.对于JPEG图像,读取图像文件中存储的量化表和JPEG系数;对于非JPEG图像,进行特定质量因子的JPEG压缩转化为JPEG格式篡改图像.将JPEG格式篡改图像进行特定质量因子的JPEG压缩,计算每一个图像子块两次压缩间的JPEG系数变化率,得到JPEG系数变化率图像JCCR.对JCCR图像进行归一化处理,实现篡改区域的检测定位.实验结果表明,采用该算法可以有效地检测JPEG图像复制粘贴篡改的多种情形,与最近的同类方法相比,具有较高的鲁棒性和检测召回率.
Abstract:
A passive detection method with the single process was proposed in order to realize the detection and localization of copy paste forgery in one image and composite forgery between two images aiming at copy paste forgery with JPEG images. A counterfeit image was made the judgement whether it was stored in JPEG format. For a JPEG image, quantization table and JPEG coefficients were read from the image file; while for a non JPEG image, it was compressed into a JPEG image with a specific quality factor. The tampered image of JPEG format was compressed with another specific quality factor. The rate of JPEG coefficients change was calculated between the two JPEG compressions in every image sub block in order to obtain the JCCR image of JPEG coefficients change rate. Normalization processing was conducted in the JCCR image in order to locate the forgery regions. Experimental results demonstrate that the proposed approach can effectively detect a variety of situations in copy paste forgery with JPEG images, and achieve higher robustness and detection recall rate compared with recent similar methods.
出版日期: 2015-10-29
:  TP 391  
基金资助:

天津市自然科学基金资助项目 (15JCYBJC15500);天津市高等学校科技发展基金计划资助项目(20120712).

通讯作者: 郭继昌,男,教授,博导.ORCID: 0000 0003 3130 1685.     E-mail: jcguo@tju.edu.cn
作者简介: 赵洁(1984— ),男,讲师,博士生,从事数字取证、多媒体信息处理的研究. ORCID: 0000 0001 6340 5580. E-mail: zhaoj@tju.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

赵洁, 郭继昌. 基于JPEG系数变化率的图像复制粘贴篡改检测[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008 973X.2015.10.010.

ZHAO Jie, GUO Ji chang. Image copy paste forgery detection based on JPEG coefficients change rate. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008 973X.2015.10.010.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008 973X.2015.10.010        http://www.zjujournals.com/eng/CN/Y2015/V49/I10/1893

[1] BIRAJDAR G, MANKAR V. Digital image forgerydetection using passive techniques: a survey [J]. Digital Investigation, 2013(10): 226-245.
[2] 赵洁,郭继昌,张艳.利用块效应特征的JPEG图像盲取证研究进展[J].中国图象图形学报, 2013, 18(6): 613-620.
ZHAO Jie, GUO Ji chang, ZHANG Yan. Survey: blind forensic of JPEG forgeries based on blocking artifacts [J]. Journal of Image and Graphics, 2013, 18(6): 613-620.
[3] LI X, ZHAO Y, LIAO M, et al. Passive detection of copy paste forgery between JPEG images [J]. Journal of Central South University, 2012, 19(10): 2839-2851.
[4] LUO W, QU Z, HUANG J, et al. A novel method for detecting cropped and recompressed image block [C]∥ Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Honolulu, HI: IEEE, 2007: 217-220.
[5] HAMDY S, EL MESSIRY H, ROUSHDY M, et al. Quantization table estimation in JPEG images [J]. International Journal of Advanced Computer Science and Applications, 2010, 1(6): 17-23.
[6] BARNI M, COSTANZO A, SABATINI L. Identification of cut & paste tampering by means of double JPEG detection and image segmentation [C]∥Proceedings of IEEE international Symposium on Circuits and Systems. Paris: IEEE, 2010: 1687-1690.
[7] YE S, SUN Q, CHANG E. Detecting digital image forgeries by measuring inconsistencies of blocking artifact [C]∥ Proceedings of IEEE International Conference on Multimedia and Expo. Beijing: IEEE, 2007: 12-15.
[8] LI W, YUAN Y, YU N. Passive detection of doctored JPEG image via block artifact grid extraction [J]. IEEE Transactions on Signal Processing, 2009, 89(9): 1821-1829.
[9] AMERINI I, BALLAN L, CALDELLI R, et al. Copy move forgery detection and localization by means of robust clustering with J Linkage [J]. Signal Processing: Image Communication, 2013, 28(6): 659-669.
[10] LI L, LI S, ZHU H, et al. Detecting copy move forgery under affine transforms for image forensics [J]. Computers and Electrical Engineering, 2014, 40(6): 1951-1962.
[11] ZHAO J, ZHAO W. Passive forensics for regionduplication image forgery based on Harris feature points and local binary patterns [J]. Mathematical Problems in Engineering, 2013, 24(4): 657-675.
[12] DAVARZANI R, YAGHMAIE K, MOZAFFARI S, et al. Copy move forgery detection using multi resolution local binary patterns [J]. Forensic Science International, 2013, 231(1/2/3): 61-72.
[13] GUO J, LIU Y, WU Z. Duplication forgery detection using improved DAISY descriptor [J]. Expert Systems with Applications, 2013, 40(2): 707-714.
[14] JABERI M, BEBIS G, HUSSAIN M, et al. Accurate and robust localization of duplication region in copy move image forgery [J]. Machine Vision and Applications, 2014, 25(2): 451-475.
[15] LIU B, PUN C, YUAN X. Digital image forgerydetection using JPEG features and local noise discrepancies [J]. The Scientific World Journal, 2014, 2014(1): 95-104.
[16] 王浩明,杨晓元.一种基于DCT系数直方图差异的JPEG图像篡改检测[J].四川大学学报:工程科学版, 2014, 46(1): 41-46.
WANG Hao ming, YANG Xiao yuan. Detection method for JPEG image based on the difference of DCTcoefficient histograms [J]. Journal of Sichuan University: Engineering Science Edition, 2014, 46(1): 41-46.
[17] McGill Calibrated Color Image Database. [2014 08 17]. http:∥tabby.vision.mcgill.ca/.
[18] Kodak Lossless True Color Image Suite. [2014 08 17]. http:∥r0k.us/graphics/kodak/.
[19] CHRISTLEIN V, RIESS C, JORDAN J, et al. Anevaluation of popular copy move forgery detectionapproaches [J]. IEEE Transactions on InformationForensics and Security, 2012, 7(6): 1841-1854.

[1] 何雪军, 王进, 陆国栋, 刘振宇, 陈立, 金晶. 基于三角网切片及碰撞检测的工业机器人三维头像雕刻[J]. 浙江大学学报(工学版), 2017, 51(6): 1104-1110.
[2] 王桦, 韩同阳, 周可. 公安情报中基于关键图谱的群体发现算法[J]. 浙江大学学报(工学版), 2017, 51(6): 1173-1180.
[3] 尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 2017, 51(6): 1163-1172.
[4] 毕晓君, 王佳荟. 基于混合学习策略的教与学优化算法[J]. 浙江大学学报(工学版), 2017, 51(5): 1024-1031.
[5] 王亮, 於志文, 郭斌. 基于双层多粒度知识发现的移动轨迹预测模型[J]. 浙江大学学报(工学版), 2017, 51(4): 669-674.
[6] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[7] 黄正宇, 蒋鑫龙, 刘军发, 陈益强, 谷洋. 基于融合特征的半监督流形约束定位方法[J]. 浙江大学学报(工学版), 2017, 51(4): 655-662.
[8] 蒋鑫龙, 陈益强, 刘军发, 忽丽莎, 沈建飞. 面向自闭症患者社交距离认知的可穿戴系统[J]. 浙江大学学报(工学版), 2017, 51(4): 637-647.
[9] 穆晶晶, 赵昕玥, 何再兴, 张树有. 基于凹凸变换与圆周拟合的重叠气泡轮廓重构[J]. 浙江大学学报(工学版), 2017, 51(4): 714-721.
[10] 戴彩艳, 陈崚, 李斌, 陈伯伦. 复杂网络中的抽样链接预测[J]. 浙江大学学报(工学版), 2017, 51(3): 554-561.
[11] 刘磊, 杨鹏, 刘作军. 采用多核相关向量机的人体步态识别[J]. 浙江大学学报(工学版), 2017, 51(3): 562-571.
[12] 郭梦丽, 达飞鹏, 邓星, 盖绍彦. 基于关键点和局部特征的三维人脸识别[J]. 浙江大学学报(工学版), 2017, 51(3): 584-589.
[13] 张亚楠, 陈德运, 王莹洁, 刘宇鹏. 基于增量图形模式匹配的动态冷启动推荐方法[J]. 浙江大学学报(工学版), 2017, 51(2): 408-415.
[14] 王海军, 葛红娟, 张圣燕. 基于核协同表示的快速目标跟踪算法[J]. 浙江大学学报(工学版), 2017, 51(2): 399-407.
[15] 刘宇鹏, 乔秀明, 赵石磊, 马春光. 统计机器翻译中大规模特征的深度融合[J]. 浙江大学学报(工学版), 2017, 51(1): 46-56.