An Evaluation of Popular Copy-Move Forgery Detection Approaches
Open accessThe DOI matches its Crossref record; 35 of the 36 references it cites were found in a registry or an index.
Abstract
A copy-move forgery is created by copying and pasting content within the same image, and potentially postprocessing it. In recent years, the detection of copy-move forgeries has become one of the most actively researched topics in blind image forensics. A considerable number of different algorithms have been proposed focusing on different types of postprocessed copies. In this paper, we aim to answer which copy-move forgery detection algorithms and processing steps (e.g., matching, filtering, outlier detection, affine transformation estimation) perform best in various postprocessing scenarios. The focus of our analysis is to evaluate the performance of previously proposed feature sets. We achieve this by casting existing algorithms in a common pipeline. In this paper, we examined the 15 most prominent feature sets. We analyzed the detection performance on a per-image basis and on a per-pixel basis. We created a challenging real-world copy-move dataset, and a software framework for systematic image manipulation. Experiments show, that the keypoint-based features Sift and Surf, as well as the block-based DCT, DWT, KPCA, PCA, and Zernike features perform very well. These feature sets exhibit the best robustness against various noise sources and downsampling, while reliably identifying the copied regions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION
(2009) · Proceedings of the Fourth International Conference on Computer Vision Theory and Applications · doi:10.5220/0001787803310340 · Cited by 2,640 · cited 1×
“In our setup we matched feature vectors using the approximate nearest neighbor method of Muja et al. [33].”
A SIFT-Based Forensic Method for Copy–Move Attack Detection and Transformation Recovery
Amerini, I., Ballan, L., Caldelli, R., Del Bimbo, A., & Serra, G. (2011) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2011.2129512 · Cited by 1,044 · cited 9×
“[3], so that the best-matching features were considered.”
InfluentialDetection of Copy-Move Forgery in Digital Images
Fridrich, J. (2004) · Cited by 1,040
Farid, H. (2009) · IEEE Signal Processing Magazine · doi:10.1109/msp.2008.931079 · Cited by 925
Shape indexing using approximate nearest-neighbour search in high-dimensional spaces
Beis, J. S., & Lowe, D. G. (2002) · Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1997.609451 · Cited by 879 · cited 1×
“rived from the kd-tree algorithm [30] to get approximate nearest neighbors [11], [20], [22].”
Rotation, scale, and translation resilient watermarking for images
Lin, C.-Y., Wu, M., Bloom, J. A., Cox, I. J., Miller, M. L., & Lui, Y. M. (2001) · IEEE Transactions on Image Processing · doi:10.1109/83.918569 · Cited by 669
An efficient and robust method for detecting copy-move forgery
Bayram, S., Taha Sencar, H., & Memon, N. (2009) · 2009 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2009.4959768 · Cited by 491 · cited 2×
“PCA [23] – SVD [13] – KPCA [4] 192 Intensity L UO [19] 7 B RAVO [7] 4 L IN [18] 9 C IRCLE [27] 8 Frequency DCT [10] 256 DWT [4] 256 FMT [6] 45 Keypoint S IFT [11], [22], [3] 128 S URF [36], [37] 64 in four categories: moment-based, dimensionality reduction-based, intensity-based, and frequency…”
Detection of Copy-Move Forgery in Digital Images Using SIFT Algorithm
Huang, H., Guo, W., & Zhang, Y. (2008) · 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application · doi:10.1109/paciia.2008.240 · Cited by 426 · cited 3×
“rived from the kd-tree algorithm [30] to get approximate nearest neighbors [11], [20], [22].”
Region Duplication Detection Using Image Feature Matching
Pan, X., & Lyu, S. (2010) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2010.2078506 · Cited by 421 · cited 9×
“From here on, we follow the algorithm by Pan and Lyu [22].”
InfluentialDetection of copy–move forgery using a method based on blur moment invariants
Mahdian, B., & Saic, S. (2007) · Forensic Science International · doi:10.1016/j.forsciint.2006.11.002 · Cited by 414 · cited 6×
“Mahdian and Saic [20] consider a pair of matched feature vectors as forged if: a) they are sufficiently similar, i.”
InfluentialThe 'Dresden Image Database' for benchmarking digital image forensics
Gloe, T., & Böhme, R. (2010) · Proceedings of the 2010 ACM Symposium on Applied Computing · doi:10.1145/1774088.1774427 · Cited by 388 · cited 2×
“For instance, the Dresden Image Database [41] is targeting methods for camera identification.”
Digital image forensics: a booklet for beginners
Redi, J. A., Taktak, W., & Dugelay, J.-L. (2011) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0620-1 · Cited by 367 · cited 1×
“T HE goal of blind image forensics is to determine the authenticity and origin of digital images without the support of an embedded security scheme (see e. g. [1], [2]).”
An efficient parts-based near-duplicate and sub-image retrieval system
Ke, Y., Sukthankar, R., & Huston, L. (2004) · Proceedings of the 12th annual ACM international conference on Multimedia · doi:10.1145/1027527.1027729 · Cited by 361
Detection of Copy-Rotate-Move Forgery Using Zernike Moments
Ryu, S.-J., Lee, M.-J., & Lee, H.-K. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-16435-4_5 · Cited by 321 · cited 3×
“[24] recently proposed the use of Zernike moments (Zernike).”
Li, G., Wu, Q., Tu, D., & Sun, S. (2007) · Multimedia and Expo, 2007 IEEE International Conference on · doi:10.1109/icme.2007.4285009 · Cited by 307 · cited 1×
“A fourth approach using a combination of the discrete wavelet transform and Singular Value Decomposition [15] did not yield reliable results in our setup and was, thus, excluded from the evaluation.”
Image Copy-Move Forgery Detection Based on SURF
Bo, X., Junwen, W., Guangjie, L., & Yuewei, D. (2010) · 2010 International Conference on Multimedia Information Networking and Security · doi:10.1109/mines.2010.189 · Cited by 253 · cited 1×
“However, particular differences of keypoint-based algorithms lie in the postprocessing of the matched features, as stated in the previous section (confer also [3], [11], [22], [36], [37]).”
Large scale test of sensor fingerprint camera identification
Goljan, M., Fridrich, J., & Filler, T. (2009) · SPIE Proceedings · doi:10.1117/12.805701 · Cited by 252 · cited 1×
“Similarly, Goljan et al. [42] presented a large-scale database for the identification of sensor fingerprints.”
Detection of Region Duplication Forgery in Digital Images Using SURF
Sons, S. (2011) · Cited by 189
Identifying Tampered Regions Using Singular Value Decomposition in Digital Image Forensics
Kang, X., & Sheng-min, W. (2008) · doi:10.1109/csse.2008.876 · Cited by 177 · cited 2×
“[13] computed the singular values of a reduced-rank approximation (SVD).”
Fast copy-move forgery detection
Lin, H.-J., Wang, C., & Kao, Y.-T. (2009) · doi:10.5555/1639329.1639332 · Cited by 156
Exploring Duplicated Regions in Natural Images
Bashar, M. K., Noda, K., Ohnishi, N., & Mori, K. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2046599 · Cited by 144 · cited 3×
“[4] proposed the Kernel-PCA (KPCA) variant of PCA.”
A semi-blind digital watermarking scheme based on singular value decomposition
Shieh, J.-M., Lou, D., & Chang, M.-C. (2005) · Computer Standards & Interfaces · doi:10.1016/j.csi.2005.03.006 · Cited by 143
A new approach for detecting Copy-Move forgery in digital images
Zhang, J., Feng, Z., & Su, Y. (2008) · IEEE International Conference on Communication Systems (ICCS) · doi:10.1109/iccs.2008.4737205 · Cited by 127 · cited 3×
“Other authors use morphological operations to connect matched pairs and remove outliers [16], [22], [26], [28].”
Exposing duplicated regions affected by reflection, rotation and scaling
Bravo-Solorio, S., & Nandi, A. K. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5946873 · Cited by 97 · cited 7×
“In contrast, Bravo-Solorio and Nandi [7] proposed the correlation coefficient between two feature vectors as a similarity criterion. c) Postprocessing: The goal of this last step is to only preserve matches that exhibit a common behavior.”
InfluentialFast and Robust Forensics for Image Region-duplication Forgery
Jun-Wen, W. A. N. G., Liu, G., Zhang, Z., Dai, Y., & Zhi-Quan, W. A. N. G. (2010) · Acta Automatica Sinica · doi:10.3724/sp.j.1004.2009.01488 · Cited by 94
Detection of Image Region Duplication Forgery Using Model with Circle Block
Wang, J., Liu, G., Li, H., Dai, Y., & Wang, Z. (2009) · International Conference on Multimedia Information Networking and Security · doi:10.1109/mines.2009.142 · Cited by 90 · cited 3×
“[27] used the mean intensities of circles with different radii around the block center (Circle).”
Detection of Region Duplication Forgery in Digital Images Using Wavelets and Log-Polar Mapping
Myna, A. N., Venkateshmurthy, M. G., & Patil, C. G. (2007) · International Conference on Computational Intelligence and Multimedia Applications (ICCIMA) · doi:10.1109/iccima.2007.271 · Cited by 87
On rotation invariance in copy-move forgery detection
Christlein, V., Rieß, C., & Angelopoulou, E. (2010) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs.2010.5711472 · Cited by 74 · cited 4×
“Alternatively, the Same Affine Transformation Selection (SATS) [8] groups locations of feature vectors to clusters.”
InfluentialSelf-citationAn Efficient Match-based Duplication Detection Algorithm
Langille, A. B., & Gong, M. (2006) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2006.9 · Cited by 66 · cited 1×
“Other authors use morphological operations to connect matched pairs and remove outliers [16], [22], [26], [28].”
A study on features for the detection of copy-move forgeries
Christlein, V., Rieß, C., & Angelopoulou, E. (2010) · Sicherheit · Cited by 61
Self-citationImage Manipulation Detection With Binary Similarity Measures
Bayram, S., Avcıbaş, İ., Sankur, B., & Memon, N. D. (2005) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.39339 · Cited by 54
Digital forgery estimation into DCT domain: a critical analysis
Battiato, S., & Messina, G. (2009) · doi:10.1145/1631081.1631091 · Cited by 34 · cited 1×
“[40] presented a tampered image database which focuses on the evaluation of detection methods based on JPEG artifacts.”
Detecting filtered cloning in digital images
Dybala, B., Jennings, B., & Letscher, D. (2007) · ACM workshop on Multimedia and security · doi:10.1145/1288869.1288877 · Cited by 26 · cited 2×
“, [4]–[7], [9], [10], [12]–[19], [21], [23]–[28]).”
Wavelet-Based Multiresolution Features for Detecting Duplications in Images
Bashar, M. K., Noda, K., Ohnishi, N., Kudo, H., Matsumoto, T., & Takeuchi, Y. (2007) · Cited by 14
An Authentication Method for Copy Areas of Images
Ju, S., Zhou, J., & He, K. (2007) · International Conference on Image and Graphics · doi:10.1109/icig.2007.120 · Cited by 10
Research works printed but not linked: 6
- [39] CASIA Image Tampering Detection Evaluation Database , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, http://forensics.idealtest.org. -
- [38] T. Ng and S. Chang, 'A Data Set of Authentic and Spliced Image Blocks,' Columbia University, Tech. Rep. 20320043, Jun. 2004. -
- [35] V. Christlein, C. Riess, J. Jordan, C. Riess, and E. Angelopoulou, 'Supplemental Material to 'An Evaluation of Popular Copy-Move Forgery Detection Approaches,' http://www.arxiv.org/abs/1208.3665, Aug. 2012. - · arXiv
- [34] R. Hartley and A. Zisserman, Multiple View Geometry . Cambridge University Press, 2003. -
- [19] W. Luo, J. Huang, and G. Qiu, 'Robust Detection of Region-Duplication Forgery in Digital Images,' in International Conference on Pattern Recognition , vol. 4, Aug. 2006, pp. 746-749. -
- [29] S. Bayram, H. T. Sencar, and N. Memon, 'A survey of copy-move forgery detection techniques,' in IEEE Western New York Image Processing Workshop , 2009. -
Cited by
Media Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
“Many datasets have been proposed specifically for copymove forgery detection [91], [92], [206], [95], [207], the forgery most studied in the literature.”
BackgroundSegmentation-Based Image Copy-Move Forgery Detection Scheme
Li, J., Li, X., Yang, B., & Sun, X. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2381872 · Cited by 810
“The first one was constructed by Christlein et al [1], consisting of 48 base images and 87 copied snippets that”
BackgroundMethodInfluentialRAISE: a raw images dataset for digital image forensics
Dang-Nguyen, D.-T., Pasquini, C., Conotter, V., & Boato, G. (2015) · Proceedings of the 6th ACM Multimedia Systems Conference · doi:10.1145/2713168.2713194 · Cited by 508
“Differently from other existing datasets targeting a specific forensic task (like splicing [12] and copy-move detection [1, 3] or source identification [10]) where the images are processed accordingly, RAISE is conceived for a general purpose within the image forensics field, since raw images contain…”
BackgroundHybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries
Bappy, J. H., Simons, C., Nataraj, L., Manjunath, B. S., & Roy-Chowdhury, A. K. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2895466 · Cited by 477
“Image Size CoMoFod [81] 260 512× 512 Manip [23] 48 2305× 3020 GRIP [25] 100 1024× 786 COVERAGE [86] 100 400× 486 Synthesized 65k 1024× 1024”
Efficient Dense-Field Copy–Move Forgery Detection
Cozzolino, D., Poggi, G., & Verdoliva, L. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2455334 · Cited by 451
“Let I (x, y) be a scalar image defined on a continuous space, (x, y) ∈ R2, and let I (ρ, θ) be its representation in polar coordinates, with ρ ∈ [0,∞] and θ ∈ [0, 2π].”
BackgroundInfluential
Metadata
- Authors
- Christlein, V., Riess, C., Jordan, J., Riess, C., & Angelopoulou, E.
- Affiliations
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- ORCID
- Riess, Christian
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2012-12
- Volume
- 7
- Issue
- 6
- Pages
- 1841-1854
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W2149073238
- Cited by
- 802
- References
- 36
- Citations by year
- 2026: 24 · 2025: 39 · 2024: 51 · 2023: 50 · 2022: 78 · 2021: 76 · 2020: 76 · 2019: 75 · 2018: 77 · 2017: 68 · 2016: 79 · 2015: 54 · 2014: 35 · 2013: 19 · 2012: 1
- FWCI
- 35.91
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Chaos-based Image/Signal Encryption
- Keywords
- copy-move forgery detection, blind image forensics, image post-processing, feature sets, SIFT, SURF, discrete cosine transform, DWT, kernel principal component analysis, principal component analysis, Zernike moments, outlier detection, affine transformation estimation, noise robustness, downsampling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.