Currently, in order to deal with color images, most forensics methods transform color images into gray images,which results in the color property not being fully used. Aimed at this problem, a copy-move forgery detection scheme based on quaternion principal component analysis (QPCA) is proposed in this paper. The scheme makes full use of the color property and the relationship among all color channels, which improves the accuracy in forged area effectively. The proposed scheme is block-based and frstly it divides images into overlapping blocks and performs QPCA of all the blocks to extract features. Then the features are lexicographical ordered to obtain shift vector and its frequency. Finally we compare the shift vector frequency to the threshold to locate the forged region. Experiments show that the missing-false alarm rate in the proposed method is lower than the existing methods and has a better accuracy.
WANG Jin-wei, XU Chun-hui
. Copy-Move Forgery Detection for Color Images Based on QPCA[J]. Journal of Applied Sciences, 2019
, 37(2)
: 291
-300
.
DOI: 10.3969/j.issn.0255-8297.2019.02.014
[1] Fridrich J, Soukal D, Lukáš J. Detection of copy-move forgery in digital image[C]//Proceedings of Digital Forensic Research Workshop, Cleveland Ohio, USA, 2003:55-61.
[2] Popescu A C, Farid H. Exposing digital forgeries by detecting duplicated image regions[R]. Department of Computer Science, Dartmouth College, Hanover, New Hampshire, 2004(2000):1-11.
[3] Ustobioglu B, Ulutus G. Improved copy-move forgery detection based on the CLDs and colour moments[J]. The Imaging Science Journal, 2016, 64(4):215-225.
[4] Zhong J L, Gan Y F. A new block-based method for copy move forgery detection under image geometric transforms[J]. Multimedia Tools and Applications, 2017, 76(13):14887-14903.
[5] Fadl S M, Semary N A E M, Hadhoud M M. A proposed accelerated image copy-move forgery detection[C]//IEEE International Conference on Visual Communications and Image Processing, 2014:253-257.
[6] Mahdian B, Saic S. Detection of copy-move forgery using a method based on blur moment invariants[J]. Forensic Science International, 2007, 171(2):180-189.
[7] Wang J, Liu G, Zhang Z, Dai Y, Wang Z. Fast and robust forensics for image region duplication forgery[J]. Acta Automatica Sinica, 2009, 35(12):1488-1495.
[8] Ryu S J, Lee M J, Lee H K. Detection of copy-rotate-move forgery using Zernike moments[C]//Proceedings of Information Hiding, 2010:51-65.
[9] Kang X, Wei S. Identifying tampered regions using singular value decomposition in digital image forensics[C]//Proceedings of Computer Science and Software Engineering, 2008:926-930.
[10] Li G H, Wu Q, Tu D, Sun S J. A sorted neighborhood approach for detecting duplicated regions in image forgeries based on DWT and SVD[C]//IEEE Proceedings of Multimedia and Expo, 2007:1750-1753.
[11] Bayram S, Sencar H, Memon N. An efcient and robust method for detecting copy-move forgery[C]//Proceedings of IEEE Intternational Conference on Acoustics, Speech and Signal Processing, 2009:1053-1056.
[12] Shivakumar B L, Baboo S. Detection of region duplication forgery in digital images using SURF[J]. International Journal of Computer Science. Issues, 2011, 8(4):199-205.
[13] Xu B, Wang J W, Liu G J. Image copy-move forgery detection based on SURF[C]//International Conference on Multimedia Information Networking & Security, 2010:889-892.
[14] Amerini I, Ballan L, Caldelli R, Bimbo A D, Serra G. 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.
[15] Huang H, Guo W, Zhang Y. Detection of copy-move forgery in digital images using SIFT algorithm[C]//Proceedings of Pacifc-Asia Workshop on Computational Intelligence and Industrial Application, 2008:272-276.
[16] Ardizzone E, Bruno A, Mazzola G. Copy-move forgery detection by matching triangles of keypoints[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(10):2084-2094.
[17] Li J, Li X L, Yang B, Sun X M. Segmentation-based image copy-move forgery detection scheme[J]. IEEE Transactions on Information Forensics and Security, 2015,10(3):507-517.
[18] Christlein V, Riess C, Jordan J, Riess C, Angelopoulou E. An evaluation of popular copy-move forgery detection approaches[J]. IEEE Transactions on Information Forensics and Security, 2012, 7(6):1841-1854.
[19] Wang J W, Li T, Shi Y Q. Forensics feature analysis in quaternion wavelet domain for distinguishing photographic images and computer graphics[J]. Multimedia Tools & Applications, 2016:10-23.
[20] 王金伟,刘仁峰. 基于QDCT马尔科夫方法的彩色图像拼接检测[J]. 应用科学学报,2017, 35(6):754-762. Wang J W, Liu R F. Splicing detection for color images based on QDCT markov method[J]. Journal of Applied Sciences, 2017, 35(6):754-762. (in Chinese)
[21] 陈北京,孙星明,王定成,赵晓平. 基于彩色图像四元数表示的彩色人脸识别[J]. 自动化学报,2012, 38(11):1815-1823. Chen B J, Sun X M, Wang D C, Zhao X P. Color face recognition using quaternion representation of color image[J]. Acta Automatica Sinica, 2012, 38(11):1815-1823. (in Chinese)
[22] Li D H, Jing L H. Color image fltering based on impulsive noise detection[C]//Proceedings of the SPIE on the ffth International Symposium on Multispectral Image Processing and Pattern Recognition, 2007:1-7.
[23] Zeng R, Wu J S, Chen B J, Shu H Z. Color image classifcation via quaternion principal component analysis network[J]. Neurocomputing, 2016:416-428.
