An End-to-End Dense-InceptionNet for Image Copy-Move Forgery Detection
The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
A novel image copy-move forgery detection scheme using a Dense-InceptionNet is proposed in this paper. Dense-InceptionNet is an end-to-end, multi-dimensional dense-feature connection, Deep Neural Network (DNN). It is the first DNN model to autonomously learn the feature correlations and search the possible forgery snippets through the matching clues. The proposed Dense-InceptionNet consists of Pyramid Feature Extractor (PFE), Feature Correlation Matching (FCM), and Hierarchical Post-Processing (HPP) modules. The PFE module is proposed to extract multi-dimensional and multi-scale dense-features. The features of each layer in this extractor module are directly connected to the preceding layers. The FCM module is proposed to learn the high correlations of deep features and obtain three candidate matching maps. Finally, the HPP module which makes use of three matching maps to obtain a combination of cross-entropies is amenable to better training via backpropagation. Experiments demonstrate that the efficiency of the proposed Dense-InceptionNet is much better than the other state-of-the-art methods while achieving the relative best performance against most known attacks.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“, Inception Net [31], [32], LeNet5 [33], Residual Networks (ResNets) [34] and VGG16 [35]) have been applied to the visual object classification, recognition and many other fields.”
BackgroundVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“With the development of the deep neural networks (DNN), there are many DNN (e.g., Inception Net [31], [32], LeNet5 [33], Residual Networks (ResNets) [34] and VGG16 [35]) have been applied to the visual object classification, recognition and many other fields.”
BackgroundGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 4×
“Wu et al. [29], [30] have introduced VGG16 as a feature extractor and Inception Net [31] as up-pooling to applying in CMFD. Inception Net has used the multiscale convolutions to obtain the multi-scale features.”
BackgroundInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 2×
“, scale-invariant feature transform (SIFT) [12]–[14] and speeded up robust features (SURF) [15], [16]) to search high-entropy regions to find the local extreme points.”
BackgroundSUN database: Large-scale scene recognition from abbey to zoo
Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539970 · Cited by 3,283
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 3×
“The CMH, MICC-F220, MICC-2000, GPIP, and Coverage datasets are also attacked by the above geometrical attacks and post-processing operations.”
BackgroundMethodDetection of Copy-Move Forgery in Digital Images
Fridrich, J. (2004) · Cited by 1,040
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
Segmentation-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 · cited 3×
“The compared methods which are listed in Table II contain classic block-based methods [2], [7], [9], [10], keypoint-based methods [15], [16], [18], [20], [21], Machine learning methods [25], [27], and DNN methods [28], [30].”
BackgroundMethodAn Evaluation of Popular Copy-Move Forgery Detection Approaches
Christlein, V., Riess, C., Jordan, J., Riess, C., & Angelopoulou, E. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2218597 · Cited by 802 · cited 10×
“Both of them have a similar framework [3]: 1) feature extraction; 2) feature matching and 3) post-processing operations.”
BackgroundMethodInfluentialA deep learning approach to detection of splicing and copy-move forgeries in images
Rao, Y., & Ni, J. (2016) · 2016 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2016.7823911 · Cited by 516 · cited 6×
“The compared methods which are listed in Table II contain classic block-based methods [2], [7], [9], [10], keypoint-based methods [15], [16], [18], [20], [21], Machine learning methods [25], [27], and DNN methods [28], [30].”
BackgroundMethodInfluentialEfficient 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 · cited 11×
“The compared methods which are listed in Table II contain classic block-based methods [2], [7], [9], [10], keypoint-based methods [15], [16], [18], [20], [21], Machine learning methods [25], [27], and DNN methods [28], [30].”
BackgroundMethodInfluentialCOVERAGE — A novel database for copy-move forgery detection
Wen, B., Zhu, Y., Subramanian, R., Ng, T.-T., Shen, X., & Winkler, S. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532339 · Cited by 440 · cited 2×
“5) Coverage [37]: the dataset has 100 base images and the corresponding forgery images with the average sizes of 400 × 486.”
BackgroundRegion 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 3×
“, scale-invariant feature transform (SIFT) [12]–[14] and speeded up robust features (SURF) [15], [16]) to search high-entropy regions to find the local extreme points.”
BackgroundMethodDetection 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 3×
“, discrete wavelet transform (DWT) [4], Discrete Cosine Transform (DCT) coefficients [5], Analytic Fourier-Mellin transform (AFMT) [2], Blur moment invariants [6], Zernike [7], Polar complex exponential transform (PCET) [8], [9], Polar cosine transform (PCT) [10], Radial Harmonic Fourier moments (RHFMs) [11], are prop…”
BackgroundBusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
Wu, Y., Abd-Almageed, W., & Natarajan, P. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_11 · Cited by 334 · cited 6×
“The compared methods which are listed in Table II contain classic block-based methods [2], [7], [9], [10], keypoint-based methods [15], [16], [18], [20], [21], Machine learning methods [25], [27], and DNN methods [28], [30].”
BackgroundMethodInfluentialCoMoFoD #x2014; New database for copy-move forgery detection
Tralić, D., Zupančić, I., Grgić, S., & Grgić, M. (2013) · Queen Mary Research Online (Queen Mary University of London) · Cited by 306
Image Forgery Detection Using Adaptive Oversegmentation and Feature Point Matching
Pun, C.-M., Yuan, X.-C., & Bi, X.-L. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2423261 · Cited by 305 · cited 4×
“The fusion methods [18]–[21] combine the feature extraction of the keypoint-based and region matting of the block-based methods.”
BackgroundMethodInfluentialSelf-citationRotation Invariant Localization of Duplicated Image Regions Based on Zernike Moments
Ryu, S.-J., Kirchner, M., Lee, M.-J., & Lee, H.-K. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2272377 · Cited by 275 · cited 10×
“The developed invariant moments, e.g., Zernike [7], PCET [9], PCT [10], with the simple kernels, excellent orthogonalities, rotation invariances, and notable robustness have been demonstrated the good feature extraction from the overlapping blocks effectively [25].”
BackgroundMethodInfluentialFast and Effective Image Copy-Move Forgery Detection via Hierarchical Feature Point Matching
Li, Y., & Zhou, J. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2876837 · Cited by 225 · cited 2×
“The fusion methods [18]–[21] combine the feature extraction of the keypoint-based and region matting of the block-based methods.”
MethodSilva, E., Carvalho, T., Ferreira, A., & Rocha, A. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.01.016 · Cited by 222
Detection and Localization of Image Forgeries Using Resampling Features and Deep Learning
Bunk, J., Bappy, J. H., Mohammed, T. M., Nataraj, L., Flenner, A., Manjunath, B. S., Chandrasekaran, S., Roy-Chowdhury, A. K., & Peterson, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.235 · Cited by 195 · cited 1×
“[24] apply DNN as a patch classifier.”
Detection of Region Duplication Forgery in Digital Images Using SURF
Sons, S. (2011) · Cited by 189
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 164 · cited 2×
“Digital Object Identifier 10.1109/TIFS.2019.2957693 algorithms, e.g., discrete wavelet transform (DWT) [4], Discrete Cosine Transform (DCT) coefficients [5], Analytic Fourier-Mellin transform (AFMT) [2], Blur moment invariants [6], Zernike [7], Polar complex exponential transform (PCET) [8], [9], Polar cosine transfor…”
BackgroundInfluentialImage Region Forgery Detection: A Deep Learning Approach
Ying, Z., Goh, J., Lei, W. L., & Thing, V. L. L. (2016) · IOS Press eBooks · doi:10.3233/978-1-61499-617-0-1 · Cited by 156 · cited 2×
“[23] apply the wavelet features of images as the input of the deep autoencoder.”
BackgroundMethodLi, Y. (2012) · Forensic Science International · doi:10.1016/j.forsciint.2012.10.031 · Cited by 150 · cited 7×
“The developed invariant moments, e.g., Zernike [7], PCET [9], PCT [10], with the simple kernels, excellent orthogonalities, rotation invariances, and notable robustness have been demonstrated the good feature extraction from the overlapping blocks effectively [25].”
BackgroundMethodInfluentialDetection of copy–move image forgery using histogram of orientated gradients
Lee, J., Chang, C.-P., & Chen, W.-K. (2015) · Information Sciences · doi:10.1016/j.ins.2015.03.009 · Cited by 146 · cited 1×
“, discrete wavelet transform (DWT) [4], Discrete Cosine Transform (DCT) coefficients [5], Analytic Fourier-Mellin transform (AFMT) [2], Blur moment invariants [6], Zernike [7], Polar complex exponential transform (PCET) [8], [9], Polar cosine transform (PCT) [10], Radial Harmonic Fourier moments (RHFMs) [11], are prop…”
BackgroundImage Copy-Move Forgery Detection via an End-to-End Deep Neural Network
Wu, Y., Abd-Almageed, W., & Natarajan, P. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00211 · Cited by 122 · cited 2×
“[29], [30] have introduced VGG16 as a feature extractor and Inception Net [31] as up-pooling to applying in CMFD.”
BackgroundMethodCopy-move forgery detection based on convolutional kernel network
Liu, Y., Guan, Q., & Zhao, X. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5374-6 · Cited by 108 · cited 2×
“[22] apply DNN as a feature extractor, and Ying et al.”
BackgroundMethodFusion of block and keypoints based approaches for effective copy-move image forgery detection
Zheng, J., Liu, Y., Ren, J., Zhu, T., Yan, Y., & Yang, H. (2016) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-016-0416-1 · Cited by 97
Multi-Level Dense Descriptor and Hierarchical Feature Matching for Copy–Move Forgery Detection
Bi, X., Pun, C., & Yuan, X. (2016) · Information Sciences · doi:10.1016/j.ins.2016.01.061 · Cited by 97 · cited 9×
“The developed invariant moments, e.g., Zernike [7], PCET [9], PCT [10], with the simple kernels, excellent orthogonalities, rotation invariances, and notable robustness have been demonstrated the good feature extraction from the overlapping blocks effectively [25].”
BackgroundSelf-citationPCET based copy-move forgery detection in images under geometric transforms
Emam, M., Han, Q., & Niu, X. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2872-2 · Cited by 93 · cited 13×
“The developed invariant moments, e.g., Zernike [7], PCET [9], PCT [10], with the simple kernels, excellent orthogonalities, rotation invariances, and notable robustness have been demonstrated the good feature extraction from the overlapping blocks effectively [25].”
BackgroundMethodInfluentialFast copy-move forgery detection using local bidirectional coherency error refinement
Bi, X., & Pun, C. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.03.028 · Cited by 79 · cited 3×
“The compared methods which are listed in Table II contain classic block-based methods [2], [7], [9], [10], keypoint-based methods [15], [16], [18], [20], [21], Machine learning methods [25], [27], and DNN methods [28], [30].”
MethodSelf-citationA two-stage localization for copy-move forgery detection
Pun, C., & Chung, J.-L. (2018) · Information Sciences · doi:10.1016/j.ins.2018.06.040 · Cited by 61 · cited 6×
“The compared methods which are listed in Table II contain classic block-based methods [2], [7], [9], [10], keypoint-based methods [15], [16], [18], [20], [21], Machine learning methods [25], [27], and DNN methods [28], [30].”
BackgroundMethodSelf-citationFast reflective offset-guided searching method for copy-move forgery detection
Bi, X., & Pun, C. (2017) · Information Sciences · doi:10.1016/j.ins.2017.08.044 · Cited by 54 · cited 1×
“Some machine learning methods, such as PatchMatch (PM) [25], Coherency Sensitive Hashing (CSH) [26], [27], are proposed to train all steps in a whole structure jointly.”
MethodSelf-citation
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
“In [131] a different architecture is devised, which includes a multiscale feature analysis and a hierarchical feature matching, which seems to better adapt to different scenarios.”
BackgroundConvolutional Neural Networks: A Survey
Krichen, M. (2023) · Computers · doi:10.3390/computers12080151 · Cited by 623
Unveiling Copy-Move Forgeries: Enhancing Detection With SuperPoint Keypoint Architecture
Diwan, A., Kumar, D., Mahadeva, R., Perera, H. C. S., & Alawatugoda, J. (2023) · IEEE Access · doi:10.1109/access.2023.3304728 · Cited by 33
Metadata
- Authors
- Zhong, J.-L., & Pun, C.-M.
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2020
- Volume
- 15
- Pages
- 2134-2146
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W2993563321
- Cited by
- 187
- References
- 38
- FWCI
- 7.82
- Type
- journal article
- Language
- en
- Open access
- closed
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.