In many court cases, surveillance videos are used as significant court evidence. As these surveillance videos can easily be forged, it may cause serious social issues, such as convicting an innocent person. Nevertheless, there is little research being done on forgery of surveillance videos. This paper proposes a forensic technique to detect forgeries of surveillance video based on sensor pattern noise (SPN). We exploit the scaling invariance of the minimum average correlation energy Mellin radial harmonic (MACE-MRH) correlation filter to reliably unveil traces of upscaling in videos. By excluding the high-frequency components of the investigated video and adaptively choosing the size of the local search window, the proposed method effectively localizes partially manipulated regions. Empirical evidence from a large database of test videos, including RGB (Red, Green, Blue)/infrared video, dynamic-/static-scene video and compressed video, indicates the superior performance of the proposed method.
References
[1]
Ng, T.T.; Chang, S.F.; Lin, C.Y.; Sun, Q. Chapter 1: Passive-Blind Image Forensics. In Multimedia Security Technologies for Digital Rights Management; Elsevier: Burlington, MA, USA, 2006; pp. 383–412.
[2]
Sencar, H.T.; Memon, N. Digital Image Forensics: There is More to a Picture Than Meets the Eye; Springer-Verlag New York Inc: New York, NY, USA, 2012.
[3]
Gallagher, A.C. Detection of Linear and Cubic Interpolation in JPEG Compressed Images. Proceedings of the 2nd Canadian Conference on Computer and Robot Vision, Washington, DC, USA, 9–11 May 2005; pp. 65–72.
[4]
Mahdian, B.; Saic, S. Blind authentication using periodic properties of interpolation. IEEE Trans. Inf. Forensic. Secur. 2008, 3, 529–538.
[5]
Prasad, S.; Ramakrishnan, K. On Resampling Detection and Its Application to Detect Image Tampering. Proceedings of IEEE International Conference on Multimedia and Security Workshop, Toronto, ON, Canada, 9–12 July 2006; pp. 1325–1328.
[6]
Popescu, A.; Farid, H. Exposing digital forgeries by detecting traces of resampling. IEEE Trans. Signal Process. 2005, 53, 758–767.
[7]
Kirchner, M. Fast and Reliable Resampling Detection by Spectral Analysis of Fixed Linear Predictor Residue. Proceedings of the 10th ACM Workshop on Multimedia and Security, New York, NY, USA, 22–23 September 2008; pp. 11–20.
[8]
Kirchner, M. Linear Row and Column Predictors for the Analysis of Resized Images. Proceedings of the 12th ACM Workshop on Multimedia and Security, New Rome, Italy, 9–10 September 2010; pp. 13–18.
[9]
Fridrich, J.; Soukal, D.; Lukas, J. Detection of Copy Move Forgery in Digital Images. Proceedings of Digital Forensic Research Workshop, Cleveland, OH, USA, 6–8 August 2003.
[10]
Wang, W.; Farid, H. Exposing Digital Forgeries in Video by Detecting Duplication. Proceedings of ACM Multimedia and Security Workshop, Dallas, TX, USA, 20–21 September 2007; pp. 35–42.
[11]
Huang, Y.; Lu, W.; Sun, W.; Long, D. Improved DCT-based detection of copy-move forgery in images. Forensic Sci. Int. 2011, 206, 178–184.
[12]
Li, G.; Wu, Q.; Tu, D.; Sun, S. A Sorted Neighborhood Approach for Detecting Duplicated Regions in Image Forgeries Based on DWT and SVD. Proceedings of IEEE International Conference on Multimedia and Expo, Bejing, China, 2–5 July 2007; pp. 1750–1753.
[13]
Luo, W.; Huang, J.; Qiu, G. Robust Detection of Region-Duplication Forgery in Digital Images. Proceedings of 18th International Conference on Pattern Recognition (ICPR 2006), Hong Kong, China, 20–24 August 2006; pp. 746–749.
[14]
Mahdian, B.; Saic, S. Detection of copy move forgery using a method based on blur moment invariants. Forensic Sci. Int. 2007, 171, 180–189.
[15]
Ryu, S.J.; Lee, M.J.; Lee, H.K. Detection of Copy-Rotate-Move Forgery Using Zernike Moments. Proceedings of International Workshop on Information Hiding, Calgary, AB, Canada, 28–30 June 2010.
[16]
Chen, M.; Fridrich, J.; Goljan, M.; Lukas, J. Determining image origin and integrity using sensor noise. IEEE Trans. Inf. Forensic. Secur. 2008, 3, 74–90.
[17]
Mondaini, N.; Caldelli, R.; Piva, A.; Barni, M.; Cappellini, V. Detection of Malevolent Changes in Digital Video for Forensic Applications. Proceedings of Security, Steganography, and Watermarking of Multimedia Contents IX, San Jose, CA, USA, 28 January 2007.
[18]
Hsu, C.C.; Hung, T.Y.; Lin, C.W.; Hsu, C.T. Video Forgery Detection Using Correlation of Noise Residue. Procesdings of 2008 IEEE 10th Workshop on Multimedia Signal Processing, Cairns, QLD, Austrilia, 8–10 October 2008; pp. 170–174.
[19]
Kobayashi, M.; Okabe, T.; Sato, Y. Detecting forgery from static-scene video based on inconsistency in noise level functions. IEEE Trans. Inf. Forensic. Secur. 2010, 5, 883–892.
[20]
Conotter, V.; O′Brien, J.F.; Farid, H. Exposing digital forgeries in ballistic motion. IEEE Trans. Inf. Forensic. Secur. 2012, 7, 283–296.
[21]
Hyun, D.K.; Lee, M.J.; Ryu, S.J.; Lee, H.Y.; Lee, H.K. Forgery Detection for Surveillance Video. Pacific-Rim Conference on Multimedia (PCM), Sydney, Australia, 20–22 December 2011; pp. 25–36.
[22]
Fridrich, J. Digital image forensics: Introducing methods that estimate and detect sensor fingerprint. IEEE Signal Process. Mag. 2009, 26, 26–37.
[23]
Chen, M.; Fridrich, J.; Goljan, M.; Lukas, J. Source Digital Camcorder Identification Using Sensor Photo-Response Non-Uniformity. Proceedings of SPIE Conference on Security, Steganography, and Watermarking of Multimedia Contents, San Jose, CA, USA, 28 January 2007.
[24]
Lukas, J.; Fridrich, J.; Goljan, M. Digital camera identification from sensor pattern noise. IEEE Trans. Inf. Forensic. Secur. 2006, 1, 205–214.
[25]
Rosenfeld, K.; Sencar, H.T. A Study of the Robustness of PRNU-based Camera Identification. Proceedings of SPIE Conference on Security, Steganography, and Watermarking of Multimedia Contents, San Jose, CA, USA, 18 January 2009.
[26]
Kerekes, R.; Kumar, B. Correlation filters with controlled scale response. IEEE Trans. Image Process. 2006, 15, 1794–1802.
[27]
Kerekes, R.A.; Vijaya Kumar, B.V.K. Selecting a composite correlation filter design: A survey and comparative study. Opt. Eng. 2008, 47, 6.
[28]
Alkanhal, M.; Vijaya Kumar, B.V.K.; Mahalanobis, A. Improving the false alarm capabilities of the maximum average correlation height correlation filter. Opt. Eng. 2000, 39, 1133–1141.
Kerekes, R.A.; Savvides, M.; Vijaya Kumar, B.V.K.; Sims, S.R.F. Fractional Power Scale-tolerant Correlation Filters for Enhanced Automatic Target Recognition Performance. Proceedings of SPIE Defense and Security Symposium, Orlando, FI, USA, 28 March 2005; pp. 317–328.
[31]
Hyun, D.K.; Ryu, S.J.; Lee, M.J.; Lee, J.H.; Lee, H.Y.; Lee, H.K. Source Camcorder Identication with Cropped and Scaled Videos. Proceedings of SPIE Conference on Media Waternarking, Security, and Forensics, Burlingame, CA, USA, 22 January 2012.
[32]
Li, C.T. Source camera identification using enhanced sensor pattern noise. IEEE Trans. Inf. Forensic. Secur. 2010, 5, 280–287.
[33]
Dillencourt, M.B.; Samet, H.; Tamminen, M. A general approach to connected-component labeling for arbitrary image representations. J. ACM 1982, 39, 253–280.
[34]
Ffdshow Encoder. Available online: https://en.wikipedia.org/wiki/Ffdshow (accessed on 6 January 2013).
