Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
Open accessThe DOI matches its Crossref record; 65 of the 65 references it cites were found in a registry or an index.
Abstract
Detecting and localizing image manipulation are necessary to counter malicious use of image editing techniques. Accordingly, it is essential to distinguish between authentic and tampered regions by analyzing intrinsic statistics in an image. We focus on JPEG compression artifacts left during image acquisition and editing. We propose a convolutional neural network that uses discrete cosine transform (DCT) coefficients, where compression artifacts remain, to localize image manipulation. Standard CNNs cannot learn the distribution of DCT coefficients because the convolution throws away the spatial coordinates, which are essential for DCT coefficients. We illustrate how to design and train a neural network that can learn the distribution of DCT coefficients. Furthermore, we introduce Compression Artifact Tracing Network that jointly uses image acquisition artifacts and compression artifacts. It significantly outperforms traditional and deep neural network-based methods in detecting and localizing tampered 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
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 2×
“Two general computer vision networks, ResNet (He et al., 2016) and HRNet (Wang et al., 2020), cannot learn compression artifacts at all.”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 5×
“People often use pretrained weights from image classification for semantic segmentation, especially from ImageNet (Krizhevsky et al., 2012).”
MethodInfluentialU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“They design a neural network based on U-Net (Ronneberger et al. 2015) and analyze the conventional semantic property by providing an RGB pixel image as input to the network.”
MethodMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“The network was implemented in PyTorch (Paszke et al., 2019) using a stochastic gradient descent optimizer with a momentum of 0.9.”
MethodInfluentialDeep High-Resolution Representation Learning for Visual Recognition
Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2983686 · Cited by 4,894
Rich Models for Steganalysis of Digital Images
Fridrich, J., & Kodovsky, J. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2190402 · Cited by 2,144 · cited 2×
“(2018) place SRM kernel (Fridrich and Kodovsky, 2012) as a pre-processing layer and uses the Faster R-CNN (Ren et al.”
MethodDigital Camera Identification From Sensor Pattern Noise
Luka, J., Fridrich, J., & Goljan, M. (2006) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2006.873602 · Cited by 1,328 · cited 4×
“The types of representative image acquisition artifacts are as follows: lens aberration (Yerushalmy and Hel-Or, 2011), sensor pattern noise (Lukas et al., 2006), interpolation traces from the color filter array (CFA) (Bammey et al., 2020), and post-processing artifacts caused by color correction,…”
BackgroundMethodInfluential”Break Our Steganographic System”: The Ins and Outs of Organizing BOSS
Bas, P., Filler, T., & Pevný, T. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24178-9_5 · Cited by 1,250 · cited 2×
“They compressed raw images (Gloe and B¨ohme, 2010; Bas et al., 2011; Dang-Nguyen et al., 2015) with 1,120 distinct quantization tables including 51 standard tables (Q50-Q100) and additional custom tables obtained from requested images to their public forensic web service.”
BackgroundA 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 1×
“Amerini et al. (2011) use a scale-invariant feature trans-6 form (SIFT) to detect copy-move forgery; the pairs of SIFT descriptors between the pristine and manipulated regions are selected using a clustering algorithm.”
MethodDeep Residual Network for Steganalysis of Digital Images
Boroumand, M., Chen, M., & Fridrich, J. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2871749 · Cited by 1,032 · cited 3×
“Boroumand et al. (2018) place unpooled layers at the early part of the network, which extracts rich features of low-level signals and illustrates excellent performance for steganalysis.”
BackgroundInfluentialMedia 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 · cited 5×
“In the field of multimedia forensics, rule-based, handcrafted feature-based and datadriven approaches to capture changes in the statistical properties of each acquisition artifact have been studied (Verdoliva, 2020).”
BackgroundInfluentialCASIA Image Tampering Detection Evaluation Database
Dong, J., Wang, W., & Tan, T. (2013) · 2013 IEEE China Summit and International Conference on Signal and Information Processing · doi:10.1109/chinasip.2013.6625374 · Cited by 813 · cited 1×
“CASIA v2 (Dong et al., 2013) is a popular dataset for copy-move and splicing forgery, images collected from several sources.”
BackgroundLearning Rich Features for Image Manipulation Detection
Zhou, P., Han, X., Morariu, V. I., & Davis, L. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00116 · Cited by 778
A mathematical analysis of the DCT coefficient distributions for images
Lam, E. Y., & Goodman, J. W. (2000) · IEEE Transactions on Image Processing · doi:10.1109/83.869177 · Cited by 707 · cited 1×
“Lam and Goodman (2000) mathematically illustrate that histograms of JPEG DCT coefficients follow the Laplacian distribution.”
BackgroundWu, Y., AbdAlmageed, W., & Natarajan, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00977 · Cited by 647 · cited 7×
“Some studies use permuted metrics without explicitly specifying ‘p-’ (Cozzolino and Verdoliva, 2019) or use a similar flipping strategy depending on ground truth (Wu et al., 2019) or prediction (Huh et al., 2018).”
BackgroundMethodInfluentialBayar, B., & Stamm, M. C. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2825953 · Cited by 599 · cited 1×
“Bayar and Stamm (2018) propose a constrained layer-based network that jointly suppresses the content of a given image and adaptively learns features from noise-like signals generated by image manipulation.”
BackgroundRAISE: 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 · cited 6×
“First, the RAISE image was compressed.”
BackgroundMethodInfluentialNoiseprint: A CNN-Based Camera Model Fingerprint
Cozzolino, D., & Verdoliva, L. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2916364 · Cited by 499 · cited 5×
“Some studies use permuted metrics without explicitly specifying ‘p-’ (Cozzolino and Verdoliva, 2019) or use a similar flipping strategy depending on ground truth (Wu et al., 2019) or prediction (Huh et al., 2018).”
BackgroundMethodInfluentialImage Forgery Localization via Fine-Grained Analysis of CFA Artifacts
Ferrara, P., Bianchi, T., De Rosa, A., & Piva, A. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2202227 · Cited by 492 · cited 9×
“The CFA is a mosaic of color filters that block out a particular portion of the spectrum, inducing each pixel to detect only one specific color among red, green, and blue (Piva, 2013).”
MethodInfluentialImage Forgery Localization via Block-Grained Analysis of JPEG Artifacts
Bianchi, T., & Piva, A. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2187516 · Cited by 459 · cited 2×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al., 2017): DBA (Ye et al., 2007), NOI1 (Mahdian and Saic, 2009), ADQ (Lin et al., 2009), NADQ (Bianchi and Piva, 2012), CFA (Ferrara et al., 2012), NOI2 (Lyu et al., 2014), and CAGI (Iakovidou et al., 2018).”
BackgroundMethodEfficient 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 4×
“For example, CAT-Net w/o D.P attains 24.60% p-F1 and 43.43% p-AP for GRIP.”
InfluentialStatistical Tools for Digital Forensics
Popescu, A. C., & Farid, H. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-30114-1_10 · Cited by 447 · cited 1×
“2.2 and Popescu and Farid (2004)).”
InfluentialFighting Fake News: Image Splice Detection via Learned Self-Consistency
Huh, M., Liu, A., Owens, A., & Efros, A. A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_7 · Cited by 442
COVERAGE — 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 1×
“COV-ERAGE (Wen et al., 2016) contains copy-move images designed to counter a similarity-based copy-move forgery detector.”
BackgroundAn Overview on Image Forensics
Piva, A. (2013) · ISRN Signal Processing · doi:10.1155/2013/496701 · Cited by 426 · cited 6×
“The CFA is a mosaic of color filters that block out a particular portion of the spectrum, inducing each pixel to detect only one specific color among red, green, and blue (Piva, 2013).”
BackgroundMethodInfluentialUsing noise inconsistencies for blind image forensics
Mahdian, B., & Saic, S. (2009) · Image and Vision Computing · doi:10.1016/j.imavis.2009.02.001 · Cited by 415 · cited 2×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al., 2017): DBA (Ye et al., 2007), NOI1 (Mahdian and Saic, 2009), ADQ (Lin et al., 2009), NADQ (Bianchi and Piva, 2012), CFA (Ferrara et al., 2012), NOI2 (Lyu et al., 2014), and CAGI (Iakovidou et al., 2018).”
MethodExposing Digital Image Forgeries by Illumination Color Classification
de Carvalho, T. J., Riess, C., Angelopoulou, E., Pedrini, H., & de Rezende Rocha, A. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2265677 · Cited by 406 · cited 1×
“Carvalho (De Carvalho et al., 2013) DSO-1 contains images of people.”
Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis
Lin, Z., He, J., Tang, X., & Tang, C.-K. (2009) · Pattern Recognition · doi:10.1016/j.patcog.2009.03.019 · Cited by 395 · cited 3×
“Then, the number of original histogram bins n ( u 2 ) contributing to bin u 2 in the double quantized histogram can be expressed as follows (Lin et al., 2009): where (cid:98)·(cid:99) is the flooring operator and (cid:100)·(cid:101) is the ceiling operator.”
BackgroundMethodThe '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×
“They compressed raw images (Gloe and B¨ohme, 2010; Bas et al., 2011; Dang-Nguyen et al., 2015) with 1,120 distinct quantization tables including 51 standard tables (Q50-Q100) and additional custom tables obtained from requested images to their public forensic web service.”
BackgroundThe Dresden Image Database for Benchmarking Digital Image Forensics
Gloe, T., & Böhme, R. (2010) · Journal of Digital Forensic Practice · doi:10.1080/15567281.2010.531500 · Cited by 378
MFC Datasets: Large-Scale Benchmark Datasets for Media Forensic Challenge Evaluation
Guan, H., Kozak, M., Robertson, E., Lee, Y., Yates, A. N., Delgado, A., Zhou, D., Kheyrkhah, T., Smith, J., & Fiscus, J. (2019) · 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw.2019.00018 · Cited by 329 · cited 2×
“NC16 SP (Guan et al., 2019) is a subset of NC16 provided by the National Institutes of Standards and Technology (NIST).”
MethodEstimation of Primary Quantization Matrix in Double Compressed JPEG Images
Lukáš, J. (2003) · Cited by 316
CoMoFoD #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
Digital image forensics via intrinsic fingerprints
Swaminathan, A., Wu, M., & Liu, K. J. R. (2008) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2007.916010 · Cited by 292
A generalized Benford's law for JPEG coefficients and its applications in image forensics
Fu, D., Shi, Y. Q., & Su, W. (2007) · SPIE Proceedings · doi:10.1117/12.704723 · Cited by 290 · cited 1×
“Fu et al. (2007) observe that the distribution of the first digits of the DCT coefficients follows Benford’s law, which is violated if the image is double compressed.”
BackgroundDetecting Digital Image Forgeries by Measuring Inconsistencies of Blocking Artifact
Ye, S., Sun, Q., & Chang, E.-C. (2007) · Multimedia and Expo, 2007 IEEE International Conference on · doi:10.1109/icme.2007.4284574 · Cited by 274 · cited 3×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al., 2017): DBA (Ye et al., 2007), NOI1 (Mahdian and Saic, 2009), ADQ (Lin et al., 2009), NADQ (Bianchi and Piva, 2012), CFA (Ferrara et al., 2012), NOI2 (Lyu et al., 2014), and CAGI (Iakovidou et al., 2018).”
MethodSPAN: Spatial Pyramid Attention Network for Image Manipulation Localization
Hu, X., Zhang, Z., Jiang, Z., Chaudhuri, S., Yang, Z., & Nevatia, R. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58589-1_19 · Cited by 261
IMD2020: A Large-Scale Annotated Dataset Tailored for Detecting Manipulated Images
Novozamsky, A., Mahdian, B., & Saic, S. (2020) · 2020 IEEE Winter Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw50321.2020.9096940 · Cited by 248
Exposing Region Splicing Forgeries with Blind Local Noise Estimation
Lyu, S., Pan, X., & Zhang, X. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-013-0688-y · Cited by 230 · cited 3×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al. 2017): DBA (Ye et al. 2007), NOI1 (Mahdian and Saic 2009), ADQ (Lin et al. 2009), NADQ (Bianchi and Piva 2012), CFA (Ferrara et al. 2012), NOI2 (Lyu et al. 2014), and CAGI (Iakovidou et al. 2018).”
BackgroundMethodRRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection
Bi, X., Wei, Y., Xiao, B., & Li, W. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00010 · Cited by 229 · cited 1×
“Bi et al. (2019) frame manipulation localization as a segmentation problem.”
BackgroundCAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing
Kwon, M.-J., Yu, I.-J., Nam, S.-H., & Lee, H.-K. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00042 · Cited by 226 · cited 2×
“This paper extends our previous study (Kwon et al., 2021), which introduced a JPEG compression artifact-tracing method for image splicing detection.”
MethodSelf-citationAligned and non-aligned double JPEG detection using convolutional neural networks
Barni, M., Bondi, L., Bonettini, N., Bestagini, P., Costanzo, A., Maggini, M., Tondi, B., & Tubaro, S. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.09.003 · Cited by 221
Multi-Scale Analysis Strategies in PRNU-Based Tampering Localization
Korus, P., & Huang, J. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2016.2636089 · Cited by 219 · cited 2×
“Because the pattern noise is an inherent property dependent on a specific camera model, it is actively used for image forensics as a distinct feature (Lukas et al., 2006; Chierchia et al., 2014; Korus and Huang, 2016).”
BackgroundA Bayesian-MRF Approach for PRNU-Based Image Forgery Detection
Chierchia, G., Poggi, G., Sansone, C., & Verdoliva, L. (2014) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2302078 · Cited by 191 · cited 2×
“Because the pattern noise is an inherent property dependent on a specific camera model, it is actively used for image forensics as a distinct feature (Lukas et al., 2006; Chierchia et al., 2014; Korus and Huang, 2016).”
BackgroundSource camera identification using footprints from lens aberration
Choi, K. S., Lam, E. Y., & Wong, K. K. Y. (2006) · SPIE Proceedings · doi:10.1117/12.649775 · Cited by 189 · cited 1×
“For source camera identification (Choi et al., 2006) and forgery detection (Yerushalmy and Hel-Or, 2011), these lens aberrations can be used as forensic fingerprints.”
Digital image integrity – a survey of protection and verification techniques
Korus, P. (2017) · Digital Signal Processing · doi:10.1016/j.dsp.2017.08.009 · Cited by 170 · cited 1×
“Consequently, in the last decade, many forensic approaches have been proposed to detect and localize image manipulation (Ver-doliva, 2020; Korus, 2017).”
BackgroundLarge-scale evaluation of splicing localization algorithms for web images
Zampoglou, M., Papadopoulos, S., & Kompatsiaris, Y. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3795-2 · Cited by 168 · cited 1×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al., 2017): DBA (Ye et al., 2007), NOI1 (Mahdian and Saic, 2009), ADQ (Lin et al., 2009), NADQ (Bianchi and Piva, 2012), CFA (Ferrara et al., 2012), NOI2 (Lyu et al., 2014), and CAGI (Iakovidou et al., 2018).”
MethodDouble JPEG compression forensics based on a convolutional neural network
Wang, Q., & Zhang, R. (2016) · EURASIP Journal on Information Security · doi:10.1186/s13635-016-0047-y · Cited by 161 · cited 9×
“, determining if a JPEG image has been compressed once or twice, is being actively studied (Wang and Zhang 2016; Park et al. 2018; Verma et al. 2020).”
BackgroundMethodInfluentialA Data Set of Authentic and Spliced Image Blocks
Ng, T.-T., & Chang, S. (2004) · Cited by 143
A Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detection
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2020) · IEEE Access · doi:10.1109/access.2020.3009877 · Cited by 135
Image 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 1×
“Similar to Wu et al. (2018) and Zhou et al. (2018), spliced images were automatically created by selecting one or more arbitrary objects in one image and pasting them onto another image at random posi-Learning tions, with random rotation and resizing.”
Digital Image Forgery Detection Based on Lens and Sensor Aberration
Yerushalmy, I., & Hel-Or, H. Z. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-010-0403-1 · Cited by 106
Double JPEG Detection in Mixed JPEG Quality Factors Using Deep Convolutional Neural Network
Park, J., Cho, D., Ahn, W., & Lee, H.-K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01228-1_39 · Cited by 100 · cited 5×
“For manipulation localization in JPEG images, the DCT volume representation is more accurate than the DCT histogram, which detects double JPEG compression (Wang and Zhang, 2016; Barni et al., 2017; Park et al., 2018).”
BackgroundMethodInfluentialSelf-citationContent-aware detection of JPEG grid inconsistencies for intuitive image forensics
Iakovidou, C., Zampoglou, M., Papadopoulos, S., & Kompatsiaris, I. Y. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.05.011 · Cited by 95 · cited 3×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al., 2017): DBA (Ye et al., 2007), NOI1 (Mahdian and Saic, 2009), ADQ (Lin et al., 2009), NADQ (Bianchi and Piva, 2012), CFA (Ferrara et al., 2012), NOI2 (Lyu et al., 2014), and CAGI (Iakovidou et al., 2018).”
MethodInfluentialAn Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics
Bammey, Q., von Gioi, R. G., & Morel, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01420 · Cited by 77 · cited 10×
“The CFA is a mosaic of color filters that block out a particular portion of the spectrum, inducing each pixel to detect only one specific color among red, green, and blue (Piva, 2013).”
BackgroundMethodInfluentialHybrid Image-Retrieval Method for Image-Splicing Validation
Pham, N. T., Lee, J. W., Kwon, G., & Park, C. (2019) · Symmetry · doi:10.3390/sym11010083 · Cited by 70 · cited 2×
“We used masks provided by a third-party user (Pham et al., 2019) because ground truth masks are not provided officially.”
MethodAn Intriguing Struggle of CNNs in JPEG Steganalysis and the OneHot Solution
Yousfi, Y., & Fridrich, J. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.2993959 · Cited by 55 · cited 2×
“Recently, Yousfi and Fridrich (2020) try to solve this problem us-ing DCT volume representation in a steganalysis clas-sification task.”
BackgroundMethodExposing splicing forgery in realistic scenes using deep fusion network
Liu, B., & Pun, C. (2020) · Information Sciences · doi:10.1016/j.ins.2020.03.099 · Cited by 50 · cited 1×
“Liu and Pun (2020) propose a fusion network that concentrates on learning low-level features and explores forensic hypotheses such as noise and JPEG discrepancies.”
BackgroundEstimation of color modification in digital images by CFA pattern change
Choi, C.-H., Lee, H.-Y., & Lee, H.-K. (2013) · Forensic Science International · doi:10.1016/j.forsciint.2012.12.014 · Cited by 50 · cited 1×
“In this process, CFA interpolation artifacts are applied to the image, and these traces can be used to detect image forgery (Bammey et al., 2020; Choi et al., 2013).”
MethodSelf-citationBlock-level double JPEG compression detection for image forgery localization
Verma, V., Singh, D., & Khanna, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15942-5 · Cited by 41 · cited 1×
“In image forensic research, double JPEG detection, i.e ., determining if a JPEG image has been compressed once or twice, is being actively stud-Learning ied (Wang and Zhang, 2016; Park et al., 2018; Verma et al., 2020).”
BackgroundManipulation Classification for JPEG Images Using Multi-Domain Features
Yu, I.-J., Nam, S.-H., Ahn, W., Kwon, M.-J., & Lee, H.-K. (2020) · IEEE Access · doi:10.1109/access.2020.3037735 · Cited by 37 · cited 1×
“The code for seven traditional methods was obtained from MKLab (Zampoglou et al. 2017): DBA (Ye et al. 2007), NOI1 (Mahdian and Saic 2009), ADQ (Lin et al. 2009), NADQ (Bianchi and Piva 2012), CFA (Ferrara et al. 2012), NOI2 (Lyu et al. 2014), and CAGI (Iakovidou et al. 2018).”
MethodSelf-citationDeep Convolutional Neural Network for Identifying Seam-Carving Forgery
Nam, S.-H., Ahn, W., Yu, I.-J., Kwon, M.-J., Son, M., & Lee, H.-K. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3037662 · Cited by 29 · cited 2×
“Inspired by computer vision tasks that have achieved significant progress after adopting CNNs, CNNs are actively exploited in image forensics to localize forged areas and detect fine-grained manipulation clues (Verdoliva, 2020; Nam et al., 2020; Yu et al., 2020).”
BackgroundSelf-citationA JPEG Corner Artifact from Directed Rounding of DCT Coefficients
Agarwal, S., & Farid, H. (2018) · Cited by 1
Cited by
TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization
Guillaro, F., Cozzolino, D., Sud, A., Dufour, N., & Verdoliva, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01974 · Cited by 275
“Eventually, we included two model-based methods: ADQ [6] that relies on JPEG artifacts, Splicebuster [10] that exploits noise artifacts; and 11 deep learning-based methods: EXIF SelfConsistency [23], Constrained R-CNN [48], RRU-Net [5], ManTraNet [46], SPAN [22], AdaCFA [2], E2E [33], CAT-Net v2 [26], IF-OSN [45], MVS…”
BackgroundMethodResultInfluentialToward real text manipulation detection: New dataset and new solution
Luo, D., Liu, Y., Yang, R., Liu, X., Zeng, J., Zhou, Y., & Bai, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2024.110828 · Cited by 25
Metadata
- Authors
- Kwon, M.-J., Nam, S.-H., Yu, I.-J., Lee, H.-K., & Kim, C.
- Venue
- International Journal of Computer Vision
- Published
- 2022-05-25
- Volume
- 130
- Issue
- 8
- Pages
- 1875-1895
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W3197106219
- Cited by
- 218
- References
- 65
- FWCI
- 11.57
- Type
- journal article
- Language
- en
- Open access
- green
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.