Camera model identification using a deep network and a reduced edge dataset

Abstract

Today, the importance of digital images as a medium for social communication is growing rapidly. Sometimes, an image needs to be authenticated by verifying its source camera model or device. Recently, deep networks have become very successful at visual pattern recognition. With this motivation, several investigators have explored the possibility of using convolutional neural networks (CNNs) for camera source identification. In this paper, we use selective preprocessing, instead of a indiscriminate one, in order not to hinder the CNN’s strong ability to learn useful features for this kind of forensic task. To generate a consistent and balanced dataset, we limit the maximum number of original images to 200 per camera model, and we discard vertically taken images. Using a relatively simple deep network structure, the proposed method achieved a better prediction accuracy—95.0%—than GoogleNet and other existing methods. Also, challenging camera models such as the Sony DSC H50 and W170 can be classified with the quite high prediction accuracies of 87.9% and 83.1%, respectively.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2

References

  1. 1.

    Holst GC, Lomheim TS (2007) CMOS/CCD sensors and camera systems, vol 408. JCD Publishing, Oviedo

    Google Scholar 

  2. 2.

    Tordoff B, Murray DW (2000) Violating rotating camera geometry: the effect of radial distortion on self-calibration. In: Proceedings of 15th international conference on pattern recognition, vol 1, pp 1423–1427

  3. 3.

    San Choi K, Lam EY, Wong KK (2006) Automatic source camera identification using the intrinsic lens radial distortion. Opt Express 14:11551–11565

    Article  Google Scholar 

  4. 4.

    Van LT, Emmanuel S, Kankanhalli MS (2007) Identifying source cell phone using chromatic aberration. In: Proceedings of IEEE international conference on multimedia and expo, pp 883–886

  5. 5.

    Gloe T, Winkler A, Borowka K (2010) Efficient estimation and large-scale evaluation of lateral chromatic aberration for digital image forensics. In: SPIE conference on media forensics and security, vol II, p 754107

  6. 6.

    Yu J, Craver S, Li E (2011) Toward the identification of DSLR lenses by chromatic aberration. In: Proceedings of SPIE: media forensics and security vol III, p 788010

  7. 7.

    Bayram S, Sencar HT, Memon N, Avcibas I (2005) Source camera identification based on CFA interpolation. In: International conference on image processing, pp 69–72

  8. 8.

    Bayram S, Sencar HT, Memon N (2006) Improvements on source camera-model identification based on CFA interpolation. In: Proceedings of international conference on digital forensics, pp 24–27

  9. 9.

    Cao H, Kot AC (2010) Mobile camera identification using demosaicing features. In: Proceedings of IEEE international symposium on circuits and systems, pp 1683–1686

  10. 10.

    Lukas J, Fridrich J, Goljan M (2006) Digital camera identification from sensor pattern noise. IEEE Trans Inf Forensics Secur 1:205–214

    Article  Google Scholar 

  11. 11.

    Goljan M, Fridrich J, Filler T (2009) Large scale test of sensor fingerprint camera identification. In: SPIE media forensics and security conference, vol 7254, p 72540I

  12. 12.

    Deng Z, Gijsenji A, Zhang J (2011) Source camera identification using auto-white balance approximation. In: International conference on computer vision, pp 57–64

  13. 13.

    Tsai MJ, Wang CS, Liu J, Yin JS (2012) Using decision fusion of feature selection in digital forensics for camera source model identification. Comput Stand Interfaces 34:292–304

    Article  Google Scholar 

  14. 14.

    Chen J, Kang X, Liu Y, Wang ZJ (2015) Median filtering forensics based on convolutional neural networks. IEEE Signal Process Lett 22:1849–1853

    Article  Google Scholar 

  15. 15.

    Xu G, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23:708–712

    Article  Google Scholar 

  16. 16.

    Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1106–1114

  17. 17.

    Baroffio L, Bondi L, Bestagini P, Tubaro S (2016) Camera identification with deep convolutional networks. arXiv preprint arXiv:1603.01068

  18. 18.

    Gloe T, Bohme R (2010) The Dresden image database for benchmarking digital image forensics. J Digit Forensic Pract 3:150–159

    Article  Google Scholar 

  19. 19.

    Tuama A, Comby F, Chaumont M (2016) Camera model identification with the use of deep convolutional neural networks. In: IEEE international workshop on information forensics and security, pp 1–6

  20. 20.

    Qian Y, Dong J, Wang W, Tan T (2015) Deep learning for steganalysis via convolutional neural networks. In: Proceedings of SPIE, vol 9409, p 94090J

  21. 21.

    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinvovich A (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition, pp 1–9

  22. 22.

    Bondi L, Güera D, Baroffio L, Bestagini P, Delp EJ, Tubaro S (2017) A preliminary study on convolutional neural networks for camera model identification. Electron Image 2017:67–76

    Article  Google Scholar 

  23. 23.

    Bondi L, Baroffio L, Güera D, Bestagini P, Delp EJ, Tubaro S (2017) First steps toward camera model identification with convolutional neural networks. IEEE Signal Process Lett 24:259–263

    Article  Google Scholar 

  24. 24.

    Owen M, Belhassen B, Stamm Matthew C (2018) Learning unified deep-features for multiple forensic tasks. In: Proceedings of the 6th ACM workshop on information hiding and multimedia security, pp 79–84

  25. 25.

    Yao H, Qiao T, Xu M, Zheng N (2018) Robust multi-classifier for camera model identification based on convolution neural network. IEEE Access 6:24973–24982

    Article  Google Scholar 

  26. 26.

    Freire-Obregòn D, Narducci F, Barra S, Castrillòn-Santana M (2018) Deep learning for source camera identification on mobile devices. Pattern Recognit Lett. https://doi.org/10.1016/j.patrec.2018.01.005

  27. 27.

    Rafi AM, Tonmoy TI, Kamal U, Hoque R, Hasan M (2019) RemNet: remnant convolutional neural network for camera model identification. arXiv:1902.00694

  28. 28.

    Yang P, Zhao W, Ni R, Zhao Y (2019) Source camera identification based on content-adaptive fusion network. Pattern Recognit Lett 119:195204

    Article  Google Scholar 

  29. 29.

    Wang Z, Wang H, Li H (2018) Camera source identification of digital images based on sample selection. KSII Trans Internet Inf Syst 12:3268–3283

    Google Scholar 

  30. 30.

    Huang Y, Zhang J, Lan X (2016) Source camera identification with imbalanced training dataset. Int J Database Theory Appl 9:205–214

    Article  Google Scholar 

  31. 31.

    Gloe T (2012) Feature-based forensic camera model identification. In: Shi YQ, Katzenbeisser S (eds) Transactions on data hiding and multimedia security VIII. LNCS. Springer, Heidelberg, pp 42–62

    Google Scholar 

Download references

Acknowledgements

This work is supported by the National Research Foundation of Korea Grant funded by Korea government (NRF-2018R1A2B6006754). We gratefully acknowledge all the people who contributed to this paper and especially the support of Government of Korea through the National Research Foundation. The Korea Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Sang-ug Kang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kang, C., Kang, Su. Camera model identification using a deep network and a reduced edge dataset. Neural Comput & Applic 32, 13139–13146 (2020). https://doi.org/10.1007/s00521-019-04619-6

Download citation

Keywords

  • Camera source identification
  • Deep learning
  • Balanced dataset
  • Edge detection