Detection of Median Filtering Manipulation in Compressed Images

Document Type : Original Article

Authors

Abstract

Median filtering, as a nonlinear content preserving process that is often employed for smoothing and denoising images, has received significant attention from the forensics and documentation research       community. In this paper, a detection scheme for median filtering of compressed images is proposed, based on singular value decomposition of the process matrix. In the proposed method, the process matrix is      obtained by linear estimation of the decoding process, implementation of median filtering and             recompression of the image. The projections of input data over eigenspaces of this process matrix is then used as features of the image. A small number of such features are utilized to classify the image as          either original or processed, thus leading to a fast and effective detection scheme for median filtering. The experimental evaluations show that the proposed scheme outperforms the existing methods, particularly over highly compressed images, and its detection error is 2% to 5% lower in comparison to the errors      introduced by other detection schemes. The singular value decomposition of the process matrix introduced in this paper, may also be used in detection of other cases of image content manipulation.
 

Keywords

References

[1]     Reverse engineering of audio-visual content data, “Deliverable D3.1, State-of-the-art on multimedia footprint detection,” FP7-ICT project REWIND, Grant Agreement no. 268478, Technical report, 2011.##
https://cordis.europa.eu/docs/projects/cnect/8/268478/080/deliverables/001-REWINDD31final.pdf##
[2]     S. Banerjee and A. Roy, “Linear Algebra and Matrix Analysis for Statistics,” (Texts in Statistical Science), 1st ed. London, U.K., Chapman and Hall/CRC, 2014.##
[3]     G. W. Stewart, “On the early history of the singular value decomposition,” SIAM Review, vol. 35, no. 4, pp. 551-566, 1993.##
[4]     A. C. Bovik, “Streaking in median filtered images,” IEEE Trans. Acoust. Speech, Signal Process. , vol. 35, no. 4, pp. 493-503, 1987.##
[5]     M. Kirchner and J. Fridrich, “On detection of median filtering in digital images,” Proc. SPIE, Media Forensics and Security II, vol. 7541, pp. 1-12, 2010.##
[6]     T. Pevny´, P. Bas, and J. Fridrich, “Steganalysis by subtractive pixel adjacency matrix,” IEEE Trans. Inf. Forensics security, vol. 5, no. 2, pp. 215-224, 2010.##
[7]     H. Yuan, “Blind forensics of median filtering in digital images,” IEEE Trans. Inf. Forensics Security, vol. 6, no. 4, pp. 1335-1345, 2011.##
[8]     C. Chen, J. Ni, R. Huang, and J. Huang, “Blind detection of median filtering in digital images: A difference domain based approach,” IEEE Trans. Image Process., vol. 22, no. 12, pp. 4699-4710, 2013.##
[9]     X. Kang, M. C. Stamm, A. Peng, and K. J. R. Liu, “Robust median filtering forensics using an autoregressive model,” IEEE Trans. Inf. Forensics  Security , vol. 8, no. 9, pp. 1456-1468, 2013.##
[10]  J. Yang, H. Ren, G. Zhu, J. Huang, and Y. Q. Shi, “Detecting median filtering via two-dimensional AR models of multiple filtered residuals,” Multimed. Tools Appl., vol. 77, no. 7, pp. 7931-7953, 2018.##
 [11]  Y. Zhang, S. Li, S. Wang, and Y. Q. Shi, “Revealing the traces of median filtering using high-order local ternary patterns,” IEEE Signal Process. Lett., vol. 21, no. 3, pp.   275-279, 2014.##
[12]  Y. Niu, Y. Zhao, and R. Ni, “Robust median filtering detection based on local difference descriptor,” Signal Process. Image Comm., vol. 53, pp. 65-72, 2017.##
[13]  J. Chen, X. Kang, Y. Liu, and Z. J. Wang, “Median filtering forensics based on convolutional neural networks,” IEEE Signal Process. Lett. , vol. 22, no. 11, pp. 1849-1853, 2015.##
[14]  W. Fan, K. Wang, and F. Cayre, “General-purpose image forensics using patch likelihood under image statistical models,” in Proc. IEEE Int. Workshop Inf. Forensics security, pp. 1-6, 2015.##
[15]  B. Bayar and M. C. Stamm, “A deep learning approach to universal image manipulation detection using a new convolutional layer,” in Proc. ACM Workshop Inf. Hiding Multimedia security, pp.5-10, 2016.##  
[16]  H. Y. Choi, H. U. Jang, D. Kim, J. Son, S. M. Mun, S. Choi, and H. K. Lee, “Detecting composite image manipulation based on deep neural networks,” in Proc. the Int. Conf. on Syst. Signal and Image Processing, IEEE, pp. 1-5, 2017.##
[17]  H. Li, W. Luo, and X. Qiu, “Identification of various image operations using residual-based features,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 28, no. 1, pp. 31-45, Jan. 2018.##
[18]  B. Bayar, and M. C. Stamm, “Constrained Convolutional Neural Networks: A New approach Towards General Purpose Image Manipulation Detection,” IEEE Tran. Inf. Forensics Security, pp. 2691-2706, 2018.##
[19]  M. Boroumand and J. Fridrich, “Deep learning for detecting processing history of images,” in Electronic Imaging, no. 7, pp. 1-9, 2018.##
[20]  C. Pasquini, G. Boato, N. Alajlan, and F. G. B. De Natale, “A deterministic approach to detect median filtering in 1D data,” IEEE Trans. Inf. Forensics Security, vol. 11, no. 7, pp. 1425-1437, 2016.##
[21]  W. Fan, K. Wang, F. Cayre, and Z. Xiong, “Median filtered image quality enhancement and anti-forensics via variational deconvolution,” IEEE Trans. Inf. Forensics Security, vol. 10, no. 5, pp. 1076-1091, 2015.##
[22]  Z. H. Wu, M. C. Stamm, and K. J. R. Liu,                   “Anti-forensics of median filtering,” in Proc. IEEE Int. Conf. Accoust. Speech, Signal Processing, pp. 3043-3047, 2013.##
[23]  H. Zeng, T. Qin, X. Kang, and L. Liu, “Countering   anti-forensics of median filtering,” in Proc. IEEE Int. Conf. Accoust. Speech, Signal Processing, pp. 2704-2708, 2014.##
[24]  V. Amanipour and S. Ghaemmaghami, “Median Filtering Forensics in Compressed Video,” IEEE Signal Process. Lett., vol. 26, no. 2, pp. 287-291, Feb. 2019.##
[25]  G. Schaefer and M. Stich, “UCID-an uncompressed color image database,” in Proc. SPIE, Storage and Retrieval Methods and Appl. for Multimedia, no. 36, pp. 472-480, 2004.##
[26]  C. C. Chang and C. J. Lin, “LIBSVM: A library for support vector machines,” ACM Trans. on Intelligent Syst. and Technol., vol. 2, no. 3, pp. 1-39, 2011.##
[27]  V. Sreekanth, A. Vedaldi, C. V. Jawahar, and A. Zisserman, “Generalized RBF feature maps for efficient detection,” in Proc. Brit. Mach. Vision Conf., pp. 1-11, 2010.##
Electronic and Cyber Defense
Volume 7, Issue 3 - Serial Number 23
November 2019
Pages 121-129

Files

History

  • Receive Date: 15 December 2018
  • Revise Date: 14 February 2019
  • Accept Date: 18 February 2019
  • Publish Date: 23 October 2019

Share

How to cite

Statistics