Rapid Image Splicing Detection Based on Relevance Vector Machine

  • Bo Su
  • Quanqiao Yuan
  • Yujin Zhang
  • Mengying Zhai
  • Shilin Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7809)


Image splicing detection has become one of the most important topics in the field of information security and much work has been done for that. We focus on its practical application, which considers not only detection rate but also the time consumption. This paper combines Run-length Histogram Features (RLHF) in spatial domain and Markov based features in frequency domain for capturing splicing artifact. Principal Component Analysis (PCA) is adopted to reduce the dimensions of the features in order to reduce the computational complexity in classification. Furthermore, this paper introduces Relevance Vector Machine (RVM) as a classifier and introduces its advantage over Support Vector Machine (SVM) in theory. Simulation shows that the performance of combined features is better than each feature alone. RVM consumes much less test time than SVM at the price of a negligible decline of detection rate. Therefore, the proposed method meets the requirements of a fast and efficient image splicing detection.


RLHF Markov PCA RVM Image Chroma 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhang, Z., Qiu, G., Sun, Q., Lin, X., Ni, Z., Shi, Y.Q.: A Unified Authentication Framework for JPEG 2000. In: IEEE International Conference on Multimedia and Expo., vol. 2, pp. 915–918. IEEE Press, New York (2004)Google Scholar
  2. 2.
    Ng, T.T., Chang, S.F., Lin, C.Y., Sun, Q.: Passive-blind Image Forensics. In: Zeng, W., Yu, H., Lin, C.Y. (eds.) Multimedia Security Technologies for Digital Rights, ch. 15, pp. 383–412. Academic Press, Missouri (2006)CrossRefGoogle Scholar
  3. 3.
    Shi, Y.Q., Chen, C., Chen, W.: A Natural Image Model Approach to Splicing Detection. In: 9th Workshop on Multimedia and Security, pp. 51–62. ACM, New York (2007)Google Scholar
  4. 4.
    Johnson, M.K., Farid, H.: Exposing Digital Forgeries by Detecting Inconsistencies in Lighting. In: 7th Workshop on Multimedia and Security, pp. 1–10. ACM, New York (2005)Google Scholar
  5. 5.
    Farid, H.: Exposing Digital Forgeries from JPEG Ghost. IEEE Transactions onInformation Forensics and Security 4(1), 154–160 (2009)CrossRefGoogle Scholar
  6. 6.
    Fridrich, J., Lukas, J.: Digital Bullet Scratches for Images. In: Proceeding of IEEE International Conference on Image Processing, Genova, Italy (2005)Google Scholar
  7. 7.
    Pan, X., Lyu, S.: Detecting image region duplication using SIFT features. In: 2010 Acoustics Speech and Signal Processing, ICASSP 2010 (2010) Google Scholar
  8. 8.
    Wang, W., Dong, J., Tan, T.: Effective image splicing detection based on image chroma. In: 2009 International Conference on Image Processing, ICIP 2009 (2009)Google Scholar
  9. 9.
    Galloway, M.M.: Texture analysis using gray level run lengths. Cornput. Graphics Image. Proc. 4, 172–179 (1975)CrossRefGoogle Scholar
  10. 10.
    Dong, J., Tan, T.N.: Blind image steganalysis based on run-length histogram analysis. In: 15th International Conference of Image Processing 2008 (ICIP 2008), pp. 2064–2067 (2008)Google Scholar
  11. 11.
    Wang, W., Dong, J., Tan, T.: Effective Image Splicing Detection Based on Image Chroma. In: 16th IEEE International Conference on Image Processing, pp. 1257–1260. IEEE Press, New York (2009)Google Scholar
  12. 12.
    Tipping, M.E.: The Relevance Vector Machine. In: Solla, S.A., Leen, T.K., Müller, K.-R. (eds.) Advances in Neural Information Processing Systems 12, pp. 652–658. MIT Press (2000)Google Scholar
  13. 13.
    Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. Journal of Machine Learning Research, 211–244 (2001)Google Scholar
  14. 14.
    Abdi, H., Williams, L.J.: Principal Component Analysis.  Wiley Interdisciplinary Reviews: Computational Statistics 2, 433–459 (2010)CrossRefGoogle Scholar
  15. 15.
    MacKay, D.J.C.: The evidence framework applied to classificationnetworks. Neural Comput. 4(5), 720–736 (1992)CrossRefGoogle Scholar
  16. 16.
    MacKay, D.J.C.: Bayesian non-linearmodeling for the prediction competition.  ASHRAE Transactions, ASHRAE 100(2), 1053–1056 (1994)Google Scholar
  17. 17.
    Columbia DVMM Research Lab. Columbia Image Splicing Detection EvaluationDataset (2004), http://www.ee.columbia.edu/ln/dvmm/downloads/authsplcuncmp/

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Bo Su
    • 1
  • Quanqiao Yuan
    • 1
  • Yujin Zhang
    • 2
  • Mengying Zhai
    • 2
  • Shilin Wang
    • 1
  1. 1.School of Information Security EngineeringShanghai Jiao Tong UniversityChina
  2. 2.Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghaiP.R. China

Personalised recommendations