A New Feature-Based Method for Source Camera Identification

  • Fanjie Meng
  • Xiangwei Kong
  • Xingang You
Part of the IFIP — The International Federation for Information Processing book series (IFIPAICT, volume 285)


The identification of image acquisition sources is an important problem in digital image forensics. This paper introduces a new feature-based method for digital camera identification. The method, which is based on an analysis of the imaging pipeline and digital camera processing operations, employs bi-coherence and wavelet coefficient features extracted from digital images. The sequential forward feature selection algorithm is used to select features, and a support vector machine is used as the classifier for source camera identification. Experiments indicate that the source camera identification method based on bi-coherence and wavelet coefficient features is both efficient and reliable.


Source camera identification bi-coherence wavelet coefficients 


  1. [1]
    I. Avcibas, Image Quality Statistics and Their Use in Steganalysis and Compression, Ph.D. Dissertation, Department of Electrical and Electronics Engineering, Bogazici University, Istanbul, Turkey, 2001.Google Scholar
  2. [2]
    I. Avcibas, N. Memon and B. Sankur, Steganalysis using image quality metrics, IEEE Transactions on Image Processing, vol. 12(2), pp. 221-229, 2003.MathSciNetCrossRefGoogle Scholar
  3. [3]
    P. Blythe and J. Fridrich, Secure digital camera, Proceedings of the Fourth Digital Forensic Research Workshop, 2004.Google Scholar
  4. [4]
    C. Chang and C. Lin, LIBSVM: A Library for Support Vector Machines (
  5. [5]
    K. Choi, E. Lam and K. Wong, Automatic source camera identification using the intrinsic lens radial distortion, Optics Express, vol. 14 (24), pp. 11551-11565, 2006.CrossRefGoogle Scholar
  6. [6]
    K. Choi, E. Lam and K. Wong, Source camera identification using footprints from lens aberration, Proceedings of the SPIE, vol. 6069, pp. 172-179, 2006.Google Scholar
  7. [7]
    F. Devernay and O. Faugeras, Automatic calibration and removal of distortion from scenes of structured environments, Proceedings of the SPIE, vol. 2567, pp. 62-72, 1995.CrossRefGoogle Scholar
  8. [8]
    J. Fackrell and S. McLaughlin, Detecting nonlinearities in speech sounds using bi-coherence, Proceedings of the Institute of Acoustics, vol. 18(9), pp. 123-130, 1996.Google Scholar
  9. [9]
    H. Farid, Blind inverse gamma correction, IEEE Transactions on Image Processing, vol. 10(10), pp. 1428-1433, 2001.CrossRefzbMATHGoogle Scholar
  10. [10]
    H. Farid and A. Popescu, Blind removal of image non-linearities, Proceedings of the Eighth International Conference on Computer Vision, vol. 1, pp. 76-81, 2001.CrossRefGoogle Scholar
  11. [11]
    H. Farid and A. Popescu, Blind removal of lens distortion, Journal of the Optical Society of America - A, vol. 18(9), pp. 2072-2078, 2001.CrossRefGoogle Scholar
  12. [12]
    Z. Geradts, J. Bijhold, M. Kieft, K. Kurosawa, K. Kuroki and N. Saitoh, Methods for identification of images acquired with digital cameras, Proceedings of the SPIE, vol. 4232, pp. 505-512, 2001.CrossRefGoogle Scholar
  13. [13]
    C. Hsu, C. Chang and C. Lin, A Practical Guide to Support Vec- tor Classification, Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan (www∼cjlin/papers/guide/guide.pdf ), 2008.Google Scholar
  14. [14]
    N. Khanna, A. Mikkilineni, A. Martone, G. Ali, G. Chiu, J. Allebach and E. Delp, A survey of forensics characterization methods for physical devices, Digital Investigation, vol. 3(S1), pp. 17-18, 2006.CrossRefGoogle Scholar
  15. [15]
    M. Kharrazi, H. Sencar and N. Memon, Blind source camera identi- fication, Proceedings of the International Conference on Image Processing, vol. 1, pp. 709-712, 2004.Google Scholar
  16. [16]
    Y. Kim and E. Powers, Digital bispectral analysis and its applica- tions to nonlinear wave interactions, IEEE Transactions on Plasma Science, vol. 7(2), pp. 120-131, 1979.CrossRefGoogle Scholar
  17. [17]
    J. Lukas, J. Fridrich and M. Goljan, Determining digital image ori- gin using sensor imperfections, Proceedings of the SPIE, vol. 5685, pp. 249-260, 2005.CrossRefGoogle Scholar
  18. [18]
    J. Lukas, J. Fridrich and M. Goljan, Digital “bullet scratches” for images, Proceedings of the International Conference on Image Processing, vol. 3, pp. 65-68, 2005.Google Scholar
  19. [19]
    J. Lukas, J. Fridrich and M. Goljan, Digital camera identification from sensor pattern noise, IEEE Transactions on Information Forensics and Security, vol. 1(2), pp. 205-214, 2005.CrossRefGoogle Scholar
  20. [20]
    S. Lyu and H. Farid, Detecting hidden messages using higher-order statistics and support vector machines, Proceedings of the Fifth International Workshop on Information Hiding, pp. 340-354, 2002.Google Scholar
  21. [21]
    S. Lyu and H. Farid, How realistic is photorealistic? IEEE Transactions on Signal Processing, vol. 53(2-2), pp. 845-850, 2005.MathSciNetCrossRefGoogle Scholar
  22. [22]
    T. Ng and S. Chang, Passive-blind image forensics, in W. Zeng, H. Yu and C. Lin (Eds.), Multimedia Security Technologies for Digital Rights, Academic Press, New York, pp. 383-412, 2006.CrossRefGoogle Scholar
  23. [23]
    T. Ng, S. Chang and Q. Sun, Blind detection of photomontage using higher order statistics, Proceedings of the International Symposium on Circuits and Systems, vol. 5, pp. 688-691, 2004.Google Scholar
  24. [24]
    P. Pudil, F. Ferri, J. Novovicova and J. Kittler, Floating search methods for feature selection with nonmonotonic criterion functions, Proceedings of Twelfth IEEE International Conference on Pattern Recognition, vol. 2, pp. 279-283, 1994.CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2008

Authors and Affiliations

  • Fanjie Meng
    • 1
  • Xiangwei Kong
    • 1
  • Xingang You
    • 2
  1. 1.Dalian University of TechnologyDalianChina
  2. 2.Beijing Electrical Technology Applications InstituteBeijingChina

Personalised recommendations