Multimedia Tools and Applications

, Volume 77, Issue 1, pp 1299–1322 | Cite as

Camera identification based on very low bit rate videos with overall noise pattern having time varying statistics

  • Nili Tian
  • Bingo Wing-Kuen Ling
  • Chunmei Qing
  • Zhijing Yang


This paper proposes a method for performing the camera identification based on very low bit rate videos with the overall noise patterns having time varying statistics. First, the overall noise pattern of each frame of each video is converted to a vector. Then, the odd order statistic moments of these vectors are computed. By performing the principal component analysis, only the most major component of each statistic moment vector is attained. These components of all the frames form a feature vector for each video. To minimize the intraclass separation and maximize the interclass separation, the linear discriminant analysis is performed. As many eigenvalues of the interclass separation matrix are close to zero, the column vectors which span the null spaces of the corresponding matrices are found and the feature vector of each video is projected to these columns and forms a new vector. It is found that these new vectors are pairwisely linear separable. Hence, a bank of perceptrons can be applied to perform the camera identification. Computer numerical simulations show that our proposed method significantly outperforms the conventional correlation based method and the conventional support vector machine based method.


Very low bit rate videos Overall noise patterns having time varying statistics Video forensics Camera identification Statistic moments Principal component analysis Linear discriminant analysis Null space approach Pairwisely linear separable Bank of perceptrons 



This work was supported partly by the National Nature Science Foundation of China (No. 61372173), the Guangdong Higher Education Engineering Technology Research Center for Big Data on Manufacturing Knowledge Patent (No. 501130144), the Hundred People Plan from the Guangdong University of Technology and the Young Thousand People Plan from the Ministry of Education of China.


  1. 1.
    Chen M, Fridrich J, Goljan, M, Lukáš, J (2007) Source digital camcorder identification using sensor photo response non-uniformity. In: Proceedings of SPIE 6505, Security, Steganography, and Watermarking of Multimedia Contents IXGoogle Scholar
  2. 2.
    Elizondo D (2006) The linear separability problem: some testing methods. IEEE Trans Neural Netw 17(2):330–344CrossRefGoogle Scholar
  3. 3.
    Ho CY-F, Ling BW-K, Lam H-K, Nasir MHU (2008) Global convergence and limit cycle behavior of weights of perceptron. IEEE Trans Neural Netw 19(6):938–947CrossRefGoogle Scholar
  4. 4.
    Kagaya M, Brendel W, Deng Q, Kesterson T, Todorovic S, Neill PJ, Zhang E (2011) Video painting with space-time-varying style parameters. IEEE Trans Vis Comput Graph 17(1):74–87CrossRefGoogle Scholar
  5. 5.
    Kumar N, Mowshowitz A (2008) Increasing internet access and freedoms with IGF participation. IEEE Internet Comput 27(2):33–36Google Scholar
  6. 6.
    Kurosawa K, Kuroki K, Saitoh N (1999) CCD fingerprint method - identification of a video camera from videotaped images. International Conference on Image Processing, ICIP 3:537–540Google Scholar
  7. 7.
    Lee PY, Hui SC, Fong ACM (2005) An intelligent categorization engine for bilingual web content filtering. IEEE Trans Multimedia 7(6):1183–1190CrossRefGoogle Scholar
  8. 8.
    Lotte F, Guan C (2011) Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Trans Biomed Eng 58(2):355–362CrossRefGoogle Scholar
  9. 9.
    Pang Y, He Y, Yuan Y, Wang K (2012) Robust CoHOG feature extraction in human-centered image/video management system. IEEE Trans Syst Man Cybern B Cybern 42(2):458–468CrossRefGoogle Scholar
  10. 10.
    Remya RS, Busra Beevi A (2015) Novel video camera authentication based on peak to correlation energy of clustered sensor pattern noise. IEEE International Conference on Engineering and Technology, ICETECH:1–5Google Scholar
  11. 11.
    Tang C, Kong AW-K, Craft N (2011) Using a knowledge-based approach to remove blocking artifacts in skin images for forensic analysis. IEEE Transactions on Information Forensics and Security 6(3):1038–1049CrossRefGoogle Scholar
  12. 12.
    van Houten W, Geradts Z (2009) Source video camera identification for multiply compressed videos originating from YouTube. Digit Investig 6:48–60CrossRefGoogle Scholar
  13. 13.
    van Houten W, Geradtes Z, Franke K, Veenman C (2010) Verification of video source camera competition (CAMCOM 2010). In: International Conference on Pattern Recognitions in Signals, Speech, Images and Videos, ICPR, Lecture Notes in Computer Science, Springer, pp 22-28Google Scholar
  14. 14.
    Villalba LJG, Orozco ALS (2016) Raquel Ramos López and Julio Hernandez Castro, "Identification of smartphone brand and model via forensic video analysis,". Expert Syst Appl 55:59–69CrossRefGoogle Scholar
  15. 15.
    Weitzner DJ (2007) Free speech and child protection on the web. IEEE Internet Comput 11(3):86–89CrossRefGoogle Scholar
  16. 16.
    Werner O (1999) Requantization for transcoding of MPEG-2 intraframes. IEEE Trans Image Process 8(2):179–191CrossRefGoogle Scholar
  17. 17.
    Wiegand T, Lightstone M, Debargha M, George Campbell T, Mitra SK (1996) Rate-distortion optimized mode selection for very low bit rate video coding and the emerging H.263 standard. IEEE Trans Circuits Syst Video Technol 6(2):182–190CrossRefGoogle Scholar
  18. 18.
    Yamamura K (1992) On piecewise-linear approximation of nonlinear mappings containing Gummel-Poon models or Shichman-Hodges models. IEEE Trans Circuits Syst I Fundam Theory Appl 39(8):694–697MathSciNetCrossRefGoogle Scholar
  19. 19.
    Yin H, Hui W, Li H, Lin C, Zhu W (2012) A novel large-scale digital forensics service platform for internet videos. IEEE Trans Multimedia 14(1):178–186CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Nili Tian
    • 1
  • Bingo Wing-Kuen Ling
    • 1
  • Chunmei Qing
    • 2
  • Zhijing Yang
    • 3
  1. 1.Faculty of Information EngineeringGuangdong University of TechnologyGuangzhouChina
  2. 2.School of Electronic and Information EngineeringSouth China University of TechnologyGuangzhouChina
  3. 3.School of Information EngineeringGuangdong University of TechnologyGuangzhouChina

Personalised recommendations