图像镜像复制粘贴篡改检测中的FI-SURF算法

doi:10.11959/j.issn.1000-436x.2015163

通信学报 ›› 2015, Vol. 36 ›› Issue (5): 54-65.doi: 10.11959/j.issn.1000-436x.2015163

图像镜像复制粘贴篡改检测中的FI-SURF算法

李岩¹,刘念²,张斌³,袁开国¹,杨义先¹

¹ 北京邮电大学信息安全中心，北京 100876
² 北京电子科技学院信息安全系，北京 100070
³ 中国信息安全认证中心，北京 100020

出版日期:2015-05-20 发布日期:2015-07-17
基金资助:
国家自然科学基金资助项目;新闻出版署基金资助项目;中央高校基本科研业务费专项基金资助项目

FI-SURF algorithm for image copy-flip-move forgery detection

IYan L¹,IUNian L²,HANGBin Z³,UANKai-guo Y¹,ANGYi-xian Y¹

¹ Information Security Center,Beijing University of Posts and Telecommunications,Beijing 100876,China
² Department of Information Security,Beijing Electronic Science and Technology Institute,Beijing 100070,China
³ China Information Security Certification Center,Beijing 100020,China

Online:2015-05-20 Published:2015-07-17
Supported by:
The National Natural Science Foundation of China;General Administration of Press and Publication of the People's Republic of China;Fundamental Research Funds for the Central Universities

摘要/Abstract

摘要：

针对数字图像版权中的复制粘贴篡改问题，提出FI-SURF (flip invariant SURF)算法。研究了当图像经过镜像翻转后SURF (speeded-up robust features)特征描述符的排列变化关系。提取SURF特征点后，将其特征描述符重新排序，即使复制粘贴区域经过镜像翻转，对应的特征点依然可以进行匹配。实验证明，FI-SURF算法在保留SURF算法运算速度快、顽健性强等优点的前提下，可有效检测出经过镜像翻转的复制粘贴区域，计算出复制粘贴区域的轮廓。

关键词: SURF, 特征点, 图像取证, 镜像翻转

Abstract:

FI-SURF (flip invariant SURF) algorithm was proposed,for the consideration of the copy-move forgery detec-tion of digital images.The arrangement of the SURF (speeded-up robust features) descriptor after image flip was studied.After extract the SURF interest points,rearrange the descriptors,the interest points can still be matched even under the condition of copy-flip-move.The experiment results show that FI-SURF not only reserved the advantage of SURF,but also can detect the copy-flip-move forgery,and can locate the duplicated region.

Key words: SURF, interest point, image forgery, copy-flip-move

李岩,刘念,张斌,袁开国,杨义先. 图像镜像复制粘贴篡改检测中的FI-SURF算法[J]. 通信学报, 2015, 36(5): 54-65.

IYan L,IUNian L,HANGBin Z,UANKai-guo Y,ANGYi-xian Y. FI-SURF algorithm for image copy-flip-move forgery detection[J]. Journal on Communications, 2015, 36(5): 54-65.

图/表 13

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

表2

图10

图11

参考文献 20

[1]	QAZI T , HAYAT K , KHAN S U , et al. Survey on blind image forgery detection[J]. IET Image Process, 2013,7(7): 660-670.
[2]	AL-QERSHI O M , KHOO B E . Passive detection of copy-move for-gery in digital images:state-of-the-art[J]. Forensic Science International, 2013,231(1-3): 284-295.
[3]	KEE E , O'BRIEN J , FARID H . Exposing photo manipulation with inconsistent shadows[J]. ACM Transactions on Graphics (TOG), 2013,32(3): 1-12.
[4]	FRIDRICH A J , SOUKAL B D , LUK ? A J . Detection of copy-move forgery in digital images[A]. Proceeding of the Digital Forensic Research Workshop[C]. Cleveland,Ohio,USA, 2003. 1-10.
[5]	POPESCU A C , FARID H , Exposing digital forgeries by detecting duplicated image regions[R]. Dept Comput Sci,Dartmouth College,Tech, 2004.
[6]	CHRISTLEIN V , RIESS C , ANGELOPOULOU E . On rotation invariance in copy-move forgery detection[A]. Proceeding of the Information Forensics and Security (WIFS)[C]. Seattle, 2010. 1-6.
[7]	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: 659-669.
[8]	LOWE D G . Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2): 91-110.
[9]	BAY H , ESS A , TUYTELAARS T , et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008,110(3): 346-359.
[10]	SHIVAKUMAR B , SANTHOSH BABOO S . Detection of region duplication forgery in digital images using SURF[J]. International Journal of Computer Science Issues (IJCSI), 2011,8(4): 199-205.
[11]	BO X , JUNWEN W , GUANGJIE L , et al. Image copy-move forgery detection based on SURF[A]. Proceeding of the Multimedia Information Networking and Security (MINES),2010 International Conference on[C]. 2010. 889-892.
[12]	QI F , WEIHONG X , QIANG L . Research of image matching based on improved SURF algorith[J]. Telkomnika Indonesian Journal of Elec-trical Engineering, 2014,12(2): 1395-1402.
[13]	PANG Y , LI W , YUAN Y , et al. Fully affine invariant SURF for image matching[J]. Neurocomputing, 2012,85: 6-10.
[14]	PAN X , LYU S . Region duplication detection using image feature matching[J]. Information Forensics and Security,IEEE Transactions on, 2010,5(4): 857-867.
[15]	GUO X , CAO X . MIFT:A framework for feature descriptors to be mirror reflection invariant[J]. Image and Vision Computing, 2012,30: 546-556.
[16]	KAKAR P , SUDHA N . Exposing postprocessed copy paste forgeries through transform-invariant features[J]. IEEE Transactions on Information Forensics and Security, 2012,7(3): 1018-1028.
[17]	AMERINI I , BALLAN L , CALDELLI R , et al. A sift-based forensic method for copy-move attack detection and transformation recovery[J]. IEEE Transactions on Information Forensics and Security, 2011,6(3): 1099-1110.
[18]	FISCHLER M A , BOLLES R C . Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981,24(6): 381-395.
[19]	SUZUKI S . Topological structural analysis of digitized binary images by border following[J]. Computer Vision,Graphics,and Image Processing, 1985,30(1): 32-46.
[20]	JEGOU H , DOUZE M , SCHMID C . Hamming embedding and weak geometric consistency for large scale image search[A]. Proceeding of the 10th European conference on Computer vision[C]. Berlin Heidelberg, 2008. 304-317.

参数名称	参数值	说明
N_pix	20	要在其N_pix像素之外的区域寻找匹配点（3.2节）
T_g2NN	0.5	g2NN匹配算法中相邻距离的比值（3.2节）
N_S	300	RANSAC算法的循环次数（3.3节）
T_BW	0.7	把ZNCC二值化时使用的阈值（3.4节）
A	0.02%	去掉ZNCC中面积小于A的孤立区域（3.4节）

算法	TPR	FPR
FI-SURF	0.961 8	0.063 7
SURF	0.484 1	0.051 0

图像镜像复制粘贴篡改检测中的FI-SURF算法

FI-SURF algorithm for image copy-flip-move forgery detection

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 20

相关文章 4

Metrics

推荐阅读 0

[1]	牛盼盼,杨思宇,王丽,杨红颖,李丽,王向阳. 基于稳健特征点的平稳小波域数字水印算法[J]. 通信学报, 2019, 40(11): 187-198.
[2]	巨刚,袁亮,刘小月,岳昊恩. 基于改进SURF算法的移动目标实时图像配准方法研究[J]. 通信学报, 2017, 38(1): 177-186.
[3]	盛国瑞，高铁杠，范礼，高琳，杨福圣，张顺. 基于扩展马尔科夫特征的Seam-Carving篡改检测[J]. 通信学报, 2014, 35(6): 6-46.
[4]	盛国瑞,高铁杠,范礼,高琳,杨福圣,张顺. 基于扩展马尔科夫特征的Seam-Carving篡改检测[J]. 通信学报, 2014, 35(6): 39-46.