Abstract
We propose a new copy-move forgery detection method, which can solve the problems of multiple copy-move forgery, low accuracy and inaccurate tampered region location. First, keypoints and corresponding features of the image are extracted by using AKAZE (accelerated KAZE). Second, features are matched by using the Hamming distance and g2NN which can detect the multiple copy-move forgery. Then, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is used to cluster the keypoints and remove false matching. Finally, PSNR (peak signal-to-noise ratio) and morphological processing is used to locate tampered region accurately. Experimental results show that the proposed method performs well on geometric transformation, post-processing, multiple copy-move forgery, and tampered region localization.
Similar content being viewed by others
REFERENCES
Z. Linna, Research on Blind Digital Image Forensics (Beijing Univ. Posts Telecommun., 2007).
S. Bravo-Solorio and A. K. Nandi, “Exposing duplicated regions affected by reflection, rotation and scaling,” in IEEE Int. Conf. on Acoustics (Prague, 2011).
S. J. Ryu, M. Kirchner, M. J. Lee, et al., “Rotation invariant localization of duplicated image regions based on zernike moments,” IEEE Trans. Inf. Forensics Secur. 8 (8), 1355–1370 (2013).
I. Amerini, L. Ballan, R. Caldelli, et al., “A SIFT-based forensic method for copy–move attack detection and transformation recovery,” IEEE Trans. Inf. Forensics Secur. 6 (3), 1099–1110 (2011).
Y. Fan, et al., “Copy-move forgery detection based on hybrid features,” J. Eng. Appl. Artif. Intel. 59, 73–83 (2017).
V. Christlein, C. Riess, J. Jordan, et al., “An evaluation of popular copy-move forgery detection approaches,” IEEE Trans. Inf. Forensics Secur. 7 (6), 1841–1854 (2012).
B. Soni, P. K. Das, and D. M. Thounaojam, “CMFD: A detailed review of block based and key feature based techniques in image copy-move forgery detection,” J. IET Image Process. 12 (2), 167–178 (2018).
P. F. Alcantarilla and T. Solutions, “Fast explicit diffusion for accelerated features in nonlinear scale spaces,” IEEE Trans. Pattern Anal. Mach. Intell. 34 (7), 1281–1298 (2011).
Z. Xuehua, S. Xuanjing, C. Haipeng, and T. Daqi, “Copy-move forgery detection based on LATCH and region-like growing,” ICIC Express Lett., Part B: Appl. 8 (10), 1429–1438 (2017).
T. Daqi, Blind Identification Algorithm of Copy-Move Tampering Area Based on ORB and Clustering (Jilin Univ., 2017).
D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vision 60 (2), 91–110 (2004).
H. Bay, T. Tuytelaars, and L. J. V. Gool, “SURF: Speeded up robust features,” in European Conference on Computer Vision (Springer, Berlin, Heidelberg, 2006).
C. S. Prakash, P. P. Panzade, H. Om, et al., “Detection of copy-move forgery using AKAZE and SIFT keypoint extraction,” Multimed. Tools Appl. 78 (16), 23535–23558 (2019).
L. Yan, L. Nian, and Z. Bin, “Image multiple copy-move forgery detection algorithm based on reversed-generalized 2 nearest-neighbor,” J. Electr. Inf. Technol. 37 (7), 147–153 (2015).
C. Liang et al., “Multi-modal joint clustering with application for unsupervised attribute discovery,” IEEE Trans. Image Process. 27 (9), 4345–4356 (2018).
L. Liu, A. Wiliem, S. Chen, et al., “What is the best way for extracting meaningful attributes from pictures?,” J. Pattern Recognit. 64, 314–326 (2016).
M. Ester, H. P. Kriegel, J. Sander, et al., “A density-based algorithm for discovering clusters in large spatial databases with noise,” in KDD’96: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (1996), pp. 226–231.
W. Bing, Research and Application of Density Clustering Algorithm (Xidian Univ., 2012).
G. Shike, D. Huailin, and L. Fei, “A method of combining density-based clustering and region growing for image segmentation,” J. Comput. Res. Dev. 44 (S3), 420–423 (2007).
F. Zhenhua, Research and Application of Clustering Algorithm Based on DBSCAN (Jiangnan Univ., 2016).
M. Zandi, A. Mahmoudi-Aznaveh, and A. Talebpour, “Iterative copy-move forgery detection based on a new interest point detector,” IEEE Trans. Inf. Forensics Secur. 11 (11), 2499–2512 (2016).
E. Ardizzone, A. Bruno, and G. Mazzola, “Copy-move forgery detection by matching triangles of keypoints,” IEEE Trans. Inf. Forensics Secur. 10 (10), 2084–2094 (2015).
Funding
The study was supported by the Research Fund Project of North China Institute of Aerospace Engineering (KY-2018-30).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest. The authors declare that they have no conflicts of interest.
Ethical approval. This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Xuehua Zhou. Born in 1989. Received her master’s degree from Jilin University in 2018 with specialty in Computer Technology. Currently work as assistant at the college of computer, North China Institute of Aerospace Engineering. Her research interests include image processing and artificial intelligence, in particular, copy-move forgery detection. Author of 1 publication.
Qingjie Shi. Born in 1990. Received his master’s degree from Beijing Jiaotong University in 2016 with specialty in Electronic and Communication Engineering. Currently work as Engineer at Zhonggong Huatong (Beijing) Technology Development Co., Ltd. His research interests include image processing, artificial intelligence, and smart highway.
Rights and permissions
About this article
Cite this article
Zhou, X.H., Shi, Q.J. Multiple Copy-Move Forgery Detection Based on Density Clustering. Pattern Recognit. Image Anal. 31, 109–116 (2021). https://doi.org/10.1134/S1054661821010181
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661821010181