基于分组SIFT的图像复制粘贴篡改快速检测算法

doi:10.11959/j.issn.1000-436x.2020045

Abstract

Abstract:

Aiming at the high computational complexity of the existing copy-move image forgery detection algorithm,a copy-move forgery detection algorithm based on group scale-invariant feature transform (SIFT) was proposed.Firstly,the simple linear iterative clustering (SLIC) was utilized to divide the input image into non-overlapping and irregular blocks.Secondly,the structure tensor was introduced to classify each block as flat blocks,edge blocks and corner blocks,and then the SIFT feature points extracted from the block were taken as the block features.Finally,the forgery was located by the inter-class matching of the block features.By means of inter-class matching and feature point matching,the time complexity of the proposed copy-move forgery detection algorithm in feature matching and locating forgery region was effectively reduced while guaranteeing the detection effect.The experimental results show that the accuracy of the proposed algorithm is 97.79%,the recall rate is 90.34%,and the F score is 93.59%,the detecting time for the image with size of 1024×768 is 12.72 s,and the detecting time for the image with size of 3000×2000 was 639.93 s.Compared with the existing copy-move algorithm,the proposed algorithm can locate the forgery region quickly and accurately,and has high robustness.

Key words: copy-move forgery detection, feature matching, SIFT, structure tensor

CLC Number:

TP391

Bin XIAO,Ruxia JING,Xiuli BI,Jianfeng MA. Fast copy-move forgery detection algorithm based on group SIFT[J]. Journal on Communications, 2020, 41(3): 62-70.

Figures/Tables 11

References 32

[1]	MOHEBBIAN E , HARIRI M . Increase the efficiency of DCT method for detection of copy-move forgery in complex and smooth images[C]// International Conference on Knowledge-based Engineering＆ Innovation. Piscataway:IEEE Press, 2015: 1147-1151.
[2]	WANG Y , TIAN L , LI C . LBP-SVD based copy move forgery detection algorithm[C]// 2017 IEEE International Symposium on Multimedia. Piscataway:IEEE Press, 2017: 553-556.
[3]	JWAID M F , BARASKAR T N . Detection of copy-move image forgery using local binary pattern with discrete wavelet transform and principle component analysis[C]// 2017 International Conference on Computing,Communication,Control and Automation. Piscataway:IEEE Press, 2017: 1-6.
[4]	ISAAC M M , WILSCY M . A key point based copy-move forgery detection using HOG features[C]// 2016 International Conference on Circuit,Power and Computing Technologies. Piscataway:IEEE Press, 2016: 1-6.
[5]	IMAMOGLU M B , ULUTAS G , ULUTAS M . Detection of copy-move forgery using Krawtchouk moment[C]// 2013 8th International Conference on Electrical and Electronics Engineering. Piscataway:IEEE Press, 2013: 311-314.
[6]	RYU S J , KIRCHNER M , LEE M J ,et al. Rotation invariant localization of duplicated image regions based on Zernike moments[J]. IEEE Transactions on Information Forensics and Security, 2013,8(8): 1355-1370.
[7]	CHEN B , YU M , SU Q ,et al. Fractional quaternion Zernike moments for robust color image copy-move forgery detection[J]. IEEE Access, 2018,PP(99):1.
[8]	BI X L , PUN C M , YUAN X C . Multi-level dense descriptor and hierarchical feature matching for copy-move forgery detection[J]. Information Sciences, 2016,345(C): 226-242.
[9]	COZZOLINO D , POGGI G , VERDOLIVA L . Efficient dense-field copy-move forgery detection[J]. IEEE Transactions on Information Forensics and Security, 2015,10(11): 2284-2297.
[10]	BRAVO-SOLORIO S , NANDI A K . Automated detection and localisation of duplicated regions affected by reflection,rotation and scaling in image forensics[J]. Signal Processing, 2011,91(8): 1759-1770.
[11]	BI X L , PUN C M . Fast copy-move forgery detection using local bidirectional coherency error refinement[J]. Pattern Recognition, 2018(81): 161-175.
[12]	LI H , LUO W , QIU X ,et al. Image forgery localization via integrating tampering possibility maps[J]. IEEE Transactions on Information Forensics and Security, 2017,12(5): 1240-1252.
[13]	DHIVYA S , SUDHAKAR B , DEVARAJAN K . 2-Level DWT based copy move forgery detection with surf features[C]// 2018 3rd International Conference on Communication and Electronics Systems. Piscataway:IEEE Press, 2018: 716-721.
[14]	YU L , HAN Q , NIU X . Feature point-based copy-move forgery detection:covering the non-textured areas[J]. Multimedia Tools and Applications, 2016,75(2): 1159-1176.
[15]	MUZAFFER G , ULUTAS G . A fast and effective digital image copy move forgery detection with binarized SIFT[C]// 2017 40th International Conference on Telecommunications and Signal Processing. Piscataway:IEEE Press, 2017: 595-598.
[16]	LUAN H , LAW N . A novel dual-threshold SIFT-based copy-move forgery detection[C]// Signal ＆ Information Processing Association Summit ＆ Conference. Piscataway:IEEE Press, 2017: 1-5.
[17]	ISAAC M M , WILSCY M . Copy-move forgery detection based on harris corner points and BRISK[C]// Proceedings of the Third International Symposium on Women in Computing and Informatics. New York:ACM Press, 2015: 394-399.
[18]	ZHENG J , LIU Y , REN J ,et al. Fusion of block and keypoints based approaches for effective copy-move image forgery detection[J]. Multidimensional Systems and Signal Processing, 2016,27(4): 989-1005.
[19]	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): 2084-2094.
[20]	DU T , TIAN L , LI C . Image copy-move forgery detection based on SIFT-BRISK[C]// 2018 International Conference on Control,Automation and Information Sciences. Piscataway:IEEE Press, 2018: 141-145.
[21]	LI Y M , ZHOU J T . Fast and effective image copy-move forgery detection via hierarchical feature point matching[J]. IEEE Transactions on Information Forensics and Security, 2018,PP99:1.
[22]	PUN C M , YUAN X C , BI X L . Image forgery detection using adaptive over-segmentation and feature point matching[J]. IEEE Transactions on Information Forensics and Security, 2015,10(8): 1705-1716.
[23]	LI J , LI X , YANG B ,et al. Segmentation-based image copy-move forgery detection scheme[J]. IEEE transactions on information forensics and security, 2014,10(3): 507-518.
[24]	ELHAMINIA B , TAHERINIA A H , HARATI A . A probabilistic framework for copy-move forgery detection based on Markov random field[J]. Multimedia Tools and Applications, 2019,78(5):2559125609.
[25]	BI X L , PUN C M , YUAN X C . Multi-scale feature extraction and adaptive matching for copy-move forgery detection[J]. Multimedia Tools and Applications, 2016,77(1): 363-385.
[26]	SHAHROUDNEJAD A , RAHMATI M . Copy-move forgery detection in digital images using affine-SIFT[C]// 2016 2nd International Conference of Signal Processing and Intelligent Systems. Piscataway:IEEE Press, 2016: 1-5.
[27]	AL-HAMMADI M M , EMMANUEL S . Improving SURF based copy-move forgery detection using super resolution[C]// 2016 IEEE International Symposium on Multimedia. Piscataway:IEEE Press, 2016: 341-344.
[28]	CHRISTLEIN V , RIESS C , JORDAN J ,et al. An evaluation of popular copy-move forgery detection approaches[J]. IEEE Transactions on Information Forensics and Security, 2012,7(6): 1841-1854.
[29]	ARSENEAU S , COOPERSTOCK J R . An improved representation of junctions through asymmetric tensor diffusion[C]// Advances in Visual Computing,Second International Symposium. Berlin:Springer, 2006: 363-372.
[30]	BIGUN J , GRANLUND G H . Optimal orientation detection of linear symmetry[C]// Proceedings of the IEEE First International Conference on Computer Vision. Piscataway:IEEE Press, 1987: 433-438.
[31]	KNUTSSON H , WESTIN C F , ANDERSSON M . Representing local structure using tensors II[C]// Scandinavian Conference on Image Analysis. Berlin:Springer, 2011: 545-556.
[32]	MAIDER J M , MIGUEL V . A spectrally weighted structure tensor for hyperspectral imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations ＆ Remote Sensing, 2016,9(9): 4442-4449.

Metrics

Recommended 0

No Suggested Reading articles found!

特征提取方法	匹配方法
DCT	穷举搜索
SVD	穷举搜索
PCA和DWT	穷举搜索
HOG	穷举搜索
Krawtchouk矩阵	穷举搜索
Zernike矩阵	近似搜索
极性复数指数变换矩阵和YCbCr颜色空间	穷举搜索
极性复数变换矩阵	近似搜索
一维描述符	穷举搜索
一致性敏感哈希	近似搜索
空间和颜色模型	近似搜索

特征提取方法	匹配方法
SURF	穷举搜索
MROGH	穷举搜索
BRISK	穷举搜索
双阈值SIFT描述符	穷举搜索
Harris角点	穷举搜索
SIFT描述符和Zernike矩阵	穷举搜索
SIFT	穷举搜索

特征提取方法	匹配方法
adaptive superpixel + SIFT descriptor	穷举搜索
SIFT descriptor	穷举搜索
polar cosine transform	近似搜索
multi-scale superpixel + SIFT descriptor	近似搜索

类型	参数	范围	步长	数量/幅
原始图像	—	—	—	36
篡改图像	—	—	—	36
篡改+旋转攻击	角度	2°～10°	2°	180
篡改+尺度缩放攻击	缩放因子	91%～109%	2%	360

ε₂	Precision	Recall	F	Time_1/s	Time_2/s
0.1	0.612 7%	0.545 4%	0.577 0%	24.164 2	2 077.559 5
0.2	0.851 3%	0.701 3%	0.769 0%	23.738 2	1 615.536 8
0.3	0.970 9%	0.903 4%	0.935 9%	12.722 9	639.933 5
0.4	0.904 7%	0.855 4%	0.879 3%	25.252 2	2 270.522 5
0.5	0.924 9%	0.843 6%	0.882 3%	28.795 1	2 573.456 5
0.6	0.940 5%	0.895 8%	0.912 9%	11.957 6	1 038.746 2
0.7	0.940 6%	0.890 4%	0.909 8%	15.112 8	1 207.580 1
0.8	0.940 6%	0.890 4%	0.909 8%	14.897 7	1 203.711 3
0.9	0.940 6%	0.890 4%	0.909 8%	17.699 3	1 489.668 1
1.0	0.940 6%	0.890 4%	0.909 8%	16.965 2	1 406.540 9

Fast copy-move forgery detection algorithm based on group SIFT

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 32

Related Articles 2

Metrics

Recommended 0

ε₁	Precision	Recall	F	Time_1/s	Time_2/s
0.1	0.921 5%	0.848 0%	0.878 1%	13.037 5	905.064 2
0.2	0.921 5%	0.848 0%	0.878 1%	13.042 6	905.475 5
0.3	0.921 5%	0.848 0%	0.878 1%	16.298 0	1 149.179 6
0.4	0.921 4%	0.853 5%	0.881 1%	15.882 6	1 147.048 5
0.5	0.876 0%	0.764 7%	0.792 0%	11.144 2	871.759 6
0.6	0.826 2%	0.755 7%	0.789 3%	12.893 5	949.070 0
0.7	0.892 7%	0.804 4%	0.846 2%	12.879 9	890.019 4
0.8	0.892 3%	0.805 7%	0.846 9%	12.679 8	901.484 0
0.9	0.970 9%	0.903 4%	0.935 9%	12.722 9	639.933 5
1.0	0.952 6%	0.880 8%	0.911 9%	12.238 1	1 544.191 9

算法	Precision	Recall	F	Time_1/s	Time_2/s
文献[11]算法	0.840 0%	0.994 3%	0.902 1%	6.624 0	74.170 0
文献[6]算法	0.959 5%	0.820 4%	0.899 7%	49.538 1	969.070 0
文献[10]算法	0.969 8%	0.760 8%	0.861 2%	121.085 6	1787.381 5
文献[22]算法	0.918 4%	0.752 6%	0.806 8%	22.377 9	986.328 7
文献[21]算法	0.946 8%	0.967 1%	0.953 8%	17.125 6	108.795 2
文献[12]算法	0.649 0%	0.164 7%	0.312 4%	108.922 4	2022.889 2
本文算法	0.970 6%	0.903 4%	0.935 9%	12.722 9	639.933 5

[1]	Guo-jun MA,Hai-dong ZHOU. Research and implementation of intelligent terminal lightweight face recognition system [J]. Journal on Communications, 2015, 36(Z1): 149-156.
[2]	. Image watermarking algorithm against attacks based on SIFT feature point and cross-ratio value [J]. Journal on Communications, 2014, 35(11): 20-180.