The forensic detection of median filtering has recently attracted the attention of the research community, mainly because of the median filtering potential uses for tampering and concealing image tampering traces in digital images. In this paper, we propose multi-scale and multi-perturbation solutions that build a highly discriminative feature space, which highlights the artifacts of median filtering by means of image quality measures. The proposed methods achieve promising results when validated with a series of real-world test cases, comprising different image compression levels, resolutions, and also a cross-dataset validation protocol.
Arias-CastroE. and DonohoD.L., Does median filtering truly preserve edges better than linear filtering? The Annals of Statistics37(3) (2009), 1172-1206.
2.
AvcibasI., BayramS., MemonN., RamkumarM. and SankurB., A classifier design for detecting image manipulations, in: IEEE Intl Conference on Image Processing (ICIP), (2004), 2645-2648.
3.
AvcibasI., MemonN. and SankurB., Steganalysis based on image quality metrics, in: IEEE Workshop on Multimedia and Signal Processing, (2001), 517-522.
4.
BovikA., Streaking in median filtered images, IEEE Transactions on Acoustic Speech and Signal Processing35(4) (1987), 493-503.
5.
CaoG., ZhaoY., NiR., YuL. and TianH., Forensic detection of median filtering in digital images, in: IEEE Intl Conference on Multimedia and Expo (ICME), (2010), 89-94.
6.
ChenC. and NiJ., Median filtering detection using edge based prediction matrix, in: Intl Conference on Digital-Forensics and Watermarking, (2012), 361-375.
7.
ChenC., NiJ. and HuangJ., Blind detection of median filtering in digital images: A difference domain based approach, IEEE Transactions on Image Processing22(12) (to appear in December, 2013), 4699-4710.
8.
ChenC., NiJ., HuangR. and HuangJ., Blind median filtering detection using statistics in difference domain, in: ACM Intl Conference on Information Hiding (IH), (2013), 1-15.
DongJ., WangW. and TanT., Casia tampered image detection evaluation database 2010, database avaiable at http:// forensics.idealtest.org/.
11.
EskiciogluA. and FisherP., Image quality measures and their performance, IEEE Transactions on Communications43(12) (1995), 2959-2965.
12.
FerreiraA. and RochaA., A multiscale and multi-perturbation blind forensic technique for median detecting, in: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications8827 (2014), 302-310.
13.
FontaniM. and BarniM., Hiding traces of median filtering in digital images, in: European Signal Processing Conference (EUSIPCO), (2012), 1239-1243.
14.
GebruI.D., Median filter detection for digital image forensics, https://isrishblog.wordpress.com/2012/08/07/median-filter-detection-for-digital-image-forensics/ August 2012.
15.
GonzalezR.C. and WoodsR.E., Digital Image Processing, 2nd edition, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA, 1992.
16.
HauckE.L., Data compression using run length encoding and statistical encoding, (2 December 1986), uS Patent 4, 626, 829.
17.
JohnsonM. and FaridH., Exposing digital forgeries through specular highlights on the eye, in: ACM Intl Conference on Information Hiding (IH), (2007), 311-325.
18.
KangX., StammM., PengA. and LiuK.J.R., Robust median filtering forensics based on the autoregressive model of median filtered residual, in: IEEE Signal Information Processing Association Annual Summit and Conference (APSIPAASC), (2012), 1-9.
19.
KangX., StammM., PengA. and LiuK.J.R., Robust median filtering forensics using an autoregressive model, IEEE Transactions on Information Forensics and Security (TIFS)8(9) (2013), 1456-1468.
20.
KeeE. and FaridH., A perceptual metric for photo retouching, Proceedings of the National Academy of Sciences108(50) (2011), 19907-19912.
21.
KirchnerM. and BohmeR., Hiding traces of resampling in digital images, IEEE Transactions on Information Forensics and Security (TIFS)3(4) (2008), 582-592.
22.
KirchnerM. and FridrichJ., On detection of median filtering in digital images, in: SPIE Media Forensics and Security II, (2010), 754110-754110-12.
23.
PevnyT., Spam features, http://dde.binghamton.edu/download/spam/, December 2011.
24.
PopescuA. and FaridH., Statistical tools for digital forensics, in: ACM Intl Workshop on Information Hiding (IH), (2004), 128-147.
25.
RochaA. and GoldensteinS., Progressive randomization: Seeing the unseen, Elsevier Computer Vision and Image Understanding (CVIU)114(3) (2010), 349-362.
26.
RochaA., ScheirerW., BoultT. and GoldensteinS., Vision of the unseen: Current trends and challenges in digital image and video forensics, ACM Computing Surveys43(4) (2011), 26:1-26:42.
27.
SaboiaP., CarvalhoT. and RochaA., Eye specular highlights telltales for digital forensics: A machine learning approach, in: Intl Conference on Image Processing (ICIP), (2011), 1977-1980.
28.
SchaeferG. and StichM., Ucid - an uncompressed colour image database, in: Storage and Retrieval Methods and Applications for Multimedia, Proceedings of SPIE5307 (2004), 472-480.
29.
StammM.C., TjoaS.K., LinW.S. and LiuK.J.R., Undetectable image tampering through jpeg compression anti-forensics, in: International Conference on Image Processing, (2010), 2109-2112.
30.
ThungK.-H. and RaveendranP., A survey of image quality measures, in: IEEE Intl Conference for Technical Postgraduates (TECHPOS), (2009), 1-4.
31.
WangZ., BovikA. and SheikhH., Image quality assessment: From error visibility to structural similarity, IEEE Transactions on Image Processing13(4) (2004), 600-612.
32.
YuanH.-D., Blind forensics of median filtering in digital images, IEEE Transactions on Information Forensics and Security (TIFS)6(4) (2011), 1335-1345.
33.
ZhangY., LiS., WangS. and ShiY.Q., Revealing the traces of median filtering using high-order local ternary patterns, IEEE Signal Processing Letters21(3) (2014), 275-279.
