A Machine Learning Based Technique for Detecting Digital Image Resampling

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9622)

Abstract

Digital images can easily be tampered because of the popularity and power editing software. In order to create a persuasive forged image, the image is usually exposed to several geometric transformations, such as rescaling and rotating. Since the manipulations require a resampling step, uncovering traces of resampling became an important approach for detecting image forgeries. In this paper, we propose a new technique to reveal image resampling artifacts. The technique employs specific features of the linear dependencies of neighboring image samples for discriminating resampled images from original images. A machine learning method is utilized for classification. Experimental results in a large dataset show that the proposed technique is good in detecting resampled images, even when the manipulated images were slightly transformed.

Keywords

Resampling Image forensics SVM Classification 

References

  1. 1.
    Katzenbeisser, S., Petitcolas, F.A.P.: Information Hiding Techniques for Steganography and Digital Watermarking. Artech House, Norwood (2000)Google Scholar
  2. 2.
    Cox, I., Miller, M., Bloom, J., Fridrich, J.: Digital Watermarking and Steganography. Morgan Kaufmann, San Francisco (2009)Google Scholar
  3. 3.
    Piva, A.: An overview on image forensics. ISRN Sig. Process. 2013, 1–22 (2013). Article ID 496701CrossRefGoogle Scholar
  4. 4.
    Prasad, S., Ramakrishnan, K.R.R.: On resampling detection and its application to detect image tampering. In: ICME 2006, pp. 1325–1328 (2006)Google Scholar
  5. 5.
    Gallagher, A.C.: Detection of linear and cubic interpolation in JPEG compressed images. In: The 2nd Canadian Conference on Computer and Robot Vision, pp. 65–72 (2005)Google Scholar
  6. 6.
    Mahdian, B., Saic, S.: Blind authentication using periodic properties of interpolation. IEEE Trans. Inf. Forensics Secur. 3, 529–538 (2008)CrossRefGoogle Scholar
  7. 7.
    Popescu, A.C., Farid, H.: Exposing digital forgeries by detecting traces of re-sampling. IEEE Trans. Signal Process. 53, 758–767 (2005)MathSciNetCrossRefGoogle Scholar
  8. 8.
    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, MM&Sec (2008)Google Scholar
  9. 9.
    Nguyen, H.C., Katzenbeisser, S.: Robust resampling detection in digital images. In: Decker, B., Chadwick, D.W. (eds.) CMS 2012. LNCS, vol. 7394, pp. 3–15. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  10. 10.
    Nguyen, H.C., Katzenbeisser, S.: Performance and robustness analysis for some re-sampling detection techniques in digital images. In: Shi, Y.Q., Kim, H.-J., Perez-Gonzalez, F. (eds.) IWDW 2011. LNCS, vol. 7128, pp. 387–397. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Wolberg, G.: Digital Image Warping. IEEE Computer Society Press, Los Alamitos (1994)Google Scholar
  12. 12.
    Oppenheim, A., Schafer, R.: Discrete-Time Signal Processing. Prentice Hall, Englewood Cliffs (1989)MATHGoogle Scholar
  13. 13.
    Gonzalez, R., Woods, R., Eddins, S.: Digital image processing using Matlab. Gatesmark Publishing, Knoxville (2009)Google Scholar
  14. 14.
    Hoilund, C.: The Radon Transform. Aalborg University (2007)Google Scholar
  15. 15.
    Beylkin, G.: Discrete radon transform. IEEE Trans. Acoust. Speech Signal Process. 35, 162–172 (1987)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Schaefer, G., Stich, M.: UCID: an uncompressed color image database. In: Proceedings of the SPIE, Storage and Retrieval Methods and Applications for Multimedia, San Jose, USA, 2004, pp. 472–480 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Faculty of Information TechnologyUniversity of Transport and CommunicationsHanoiVietnam

Personalised recommendations