Camera Source Identification with Limited Labeled Training Set

  • Yue Tan
  • Bo Wang
  • Ming Li
  • Yanqing Guo
  • Xiangwei Kong
  • Yunqing Shi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9569)

Abstract

This paper investigates the problem of model-based camera source identification with limited labeled training samples. We consider the realistic scenario in which the number of labeled training samples is limited. Ensemble projection (EP) method is proposed by introducing prototype theory into semi-supervised learning. After constructing sub-sets of local binary patterns (LBP) features, several pre-classifiers are established for all labeled and unlabeled samples. According to the ranking of posterior probabilities, several prototype sets are constructed for the ensemble projection. Combining the outputs of all labeled samples from classifiers trained by prototype sets, a new feature vector is generated for camera source identification. Experimental results illustrate that the proposed EP method achieves a notable higher average accuracy than previous algorithms when labeled training samples is limited.

Keywords

Camera source identification Limited labeled training samples Ensemble projection LBP features 

References

  1. 1.
    Fridrich, J., Lukáš, J., Goljan, M.: Digital camera identifica-tion from sensor pattern noise. IEEE Trans. Inf. Forensics Secur. 12, 205–214 (2006)Google Scholar
  2. 2.
    Yu, B., Hu, Y., Jian, C.: Source camera identification using large components of sensor pattern noise. In: Proceedings of International Conference on Computer Science and its Applications, pp. 1–5 (2009)Google Scholar
  3. 3.
    Hu, Y., Li, C.-T., Jian, C.: Building fingerprints with infor-mation from three color bands for source camera identification. In: Proceedings of ACM Workshop on Multimedia in Forensics, Security and Intelligence, New York, pp. 111–116 (2010)Google Scholar
  4. 4.
    Li, C.-T.: Source camera identification using enhanced sensor pattern noise. IEEE Trans. Inf. Forensics Secur. 5(2), 280–287 (2010)CrossRefGoogle Scholar
  5. 5.
    Hu, Y., Jian, C., Li, C.-T.: Using improved imaging sensor pattern noise for source camera identification. In: Proceedings of IEEE International Conference on Multimedia & Expo (ICME), Singapore, pp. 1481–1486 (2010)Google Scholar
  6. 6.
    Kang, X., Li, Y., Qu, Z.: Enhanced source camera identifi-cation performance with a camera reference phase sensor pattern noise. IEEE Trans. Inf. Forensics Secur. 7(2), 393–402 (2012)CrossRefGoogle Scholar
  7. 7.
    Fridrich, J.: Sensor defects in digital image forensic. In: Sencar, H.T., Memon, N. (eds.) Digital Image Forensics, pp. 179–218. Springer, New York (2013)CrossRefGoogle Scholar
  8. 8.
    Swaminathan, A., Wu, M., Liu, K.J.R.: Nonintrusive com-ponent forensics of visual sensors using output images. IEEE Trans. Inf. Forensics Secur. 2(1), 91–105 (2007)CrossRefGoogle Scholar
  9. 9.
    Celiktutan, O., Sankur, B., Avcibas, I.: Blind identification of source cell-phone model. IEEE Trans. Inf. Forensics Secur. 3(3), 553–566 (2008)CrossRefGoogle Scholar
  10. 10.
    Xu, G., Shi, Y.Q.: Camera model identification using local binary patterns. In: Proceedings of IEEE International Conference on Multimedia & Expo (ICME), Melbourne, Australia, pp. 392–397 (2012)Google Scholar
  11. 11.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)CrossRefMATHGoogle Scholar
  12. 12.
    Roach, E., Lloyd, B.B.: Cognition and Categorization, Mul-timedia Systems. Hillsdale, New Jersey (1978)Google Scholar
  13. 13.
    Gärdenfors, P.: Conceptual Spaces: The Geometry of Thought. England, London (2000)Google Scholar
  14. 14.
    Dai, D., Gool, L.V.: Ensemble projection for semi-surpervised image classification. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, pp. 2072–2079 (2013)Google Scholar
  15. 15.
    Gloe, T., Bohme, R.: The ’Dresden Image Database’ for benchmarking digital image forensics. In: Proceedings of ACM Symposium on Applied Computing, Sierre, Switzerland, vol. 3(2–4) (2010)Google Scholar
  16. 16.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machine. ACM Trans. Intell. Syst. Technol. N.Y. 2(3), 27:1–27:27 (2011). Software, [Online]. Avaliable: http://www.cise.edu.tw/ cjlin/libsvm Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Yue Tan
    • 1
  • Bo Wang
    • 1
  • Ming Li
    • 1
  • Yanqing Guo
    • 1
  • Xiangwei Kong
    • 1
  • Yunqing Shi
    • 2
  1. 1.Dalian University of TechnologyDalianChina
  2. 2.New Jersey Institute of TechnologyNewarkUSA

Personalised recommendations