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

  • Changhee Kang
  • Sang-ug KangEmail author
Green and Human Information Technology 2019


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.


Camera source identification Deep learning Balanced dataset Edge detection 



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.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Holst GC, Lomheim TS (2007) CMOS/CCD sensors and camera systems, vol 408. JCD Publishing, OviedoGoogle 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 1423–1427Google Scholar
  3. 3.
    San Choi K, Lam EY, Wong KK (2006) Automatic source camera identification using the intrinsic lens radial distortion. Opt Express 14:11551–11565CrossRefGoogle 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 883–886Google Scholar
  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 754107Google Scholar
  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 788010Google Scholar
  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 69–72Google Scholar
  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 24–27Google Scholar
  9. 9.
    Cao H, Kot AC (2010) Mobile camera identification using demosaicing features. In: Proceedings of IEEE international symposium on circuits and systems, pp 1683–1686Google Scholar
  10. 10.
    Lukas J, Fridrich J, Goljan M (2006) Digital camera identification from sensor pattern noise. IEEE Trans Inf Forensics Secur 1:205–214CrossRefGoogle 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 72540IGoogle Scholar
  12. 12.
    Deng Z, Gijsenji A, Zhang J (2011) Source camera identification using auto-white balance approximation. In: International conference on computer vision, pp 57–64Google Scholar
  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 34:292–304CrossRefGoogle Scholar
  14. 14.
    Chen J, Kang X, Liu Y, Wang ZJ (2015) Median filtering forensics based on convolutional neural networks. IEEE Signal Process Lett 22:1849–1853CrossRefGoogle Scholar
  15. 15.
    Xu G, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23:708–712CrossRefGoogle 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 1106–1114Google Scholar
  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 3:150–159CrossRefGoogle 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 1–6Google Scholar
  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 94090JGoogle Scholar
  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 1–9Google Scholar
  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 2017:67–76CrossRefGoogle 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 24:259–263CrossRefGoogle 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 79–84Google Scholar
  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 6:24973–24982CrossRefGoogle 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. CrossRefGoogle Scholar
  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 119:195204CrossRefGoogle 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 12:3268–3283Google Scholar
  30. 30.
    Huang Y, Zhang J, Lan X (2016) Source camera identification with imbalanced training dataset. Int J Database Theory Appl 9:205–214CrossRefGoogle 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 42–62CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceSangmyung UniversityJongno-GuKorea
  2. 2.Faculty of Computer ScienceSangmyung UniversityJongno-GuKorea

Personalised recommendations