Blind Forensics of Median Filtering Based on Markov Statistics in Median-Filtered Residual Domain
Revealing the processing history of a digital image has received a great deal of attention from forensic analyzers in recent years. Median filtering is a non-linear operation and has been used widely for noise removal and image enhancement. Therefore, exposing the traces introduced by such operation is helpful to forensic analyzers. In this paper, a passive forensic method to detect median filtering in digital images is proposed. Since overlapped window filtering introduces the correlation among the elements of the median-filtered residual (MFR) which is referred to as the difference between a test image and its corresponding median-filtered version, the transition probability matrices along the horizontal, vertical, main diagonal and minor diagonal directions are calculated from the MFR to characterize the correlation among the elements of the MFR. All elements of these transition probability matrices are served as discriminative features for median filtering detection. Experiment results demonstrate the effectiveness of the proposed method.
KeywordsImage forensics Median filtering Median-filtered residual
This work is funded by National Science Foundation of China (61271316, 61071152, and 61271180), 973 Program (2010CB731403, 2010CB731406, and 2013CB329605) of China, Chinese National “Twelfth Five-Year” Plan for Science & Technology Support (2012BAH38 B04), Key Laboratory for Shanghai Integrated Information Security Management Technology Research, and Chinese National Engineering Laboratory for Information Content Analysis Technology. We would like to thank Prof. Yuan for his kindness by providing us with the code of the MFF scheme in .
- 3.Shi YQ, Chen C, Chen W (2007) A natural image model approach to splicing detection. In: Proceedings of ACM Multimedia and Security Workshop, Dallas, TX, 20–21 September, 2007, pp. 51–62Google Scholar
- 5.Kirchner M, Fridrich J (2010) On detection of median filtering in digital images. Proc SPIE Electron Imag Med Forensics Secur II 7541:1–12Google Scholar
- 6.Cao G, Zhao Y, Ni R, Yu L, Tian H (2010) Forensic detection of median filtering in digital images. In: Proceedings of the 2010 I.E. international conference on multimedia and expo, Suntec City, 19–23 July, 2010, pp. 89–94Google Scholar
- 8.Chen C, Ni J, Huang R, Huang J (2013) Blind median filtering detection using statistics in difference domain. In: Proceedings of 14th information hiding. LNCS 7692:1–15Google Scholar
- 9.Kang X, Stamm MC, Peng A, Liu KJR (2012) Robust median filtering forensics based on the autoregressive model of median filtered residual. In: Proceedings of signal & information processing association annual summit and conference, Hollywood, CA, 3–6 December, 2012, pp. 1–9
- 11.NRCS Photo Gallery [Online]: http://photogallery.nrcs.usda.gov/res/sites/photogallery/
- 12.Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines [Online]. http://www.csie.ntu.edu.tw/cjlin/libsvm