The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

Camera Model Identification Using Modified DenseNet and HPF

변형된 DenseNet과 HPF를 이용한 카메라 모델 판별 알고리즘

  • 이수현 (금오공과대학교 소프트웨어공학과) ;
  • 김동현 (금오공과대학교 소프트웨어공학과) ;
  • 이해연 (금오공과대학교 컴퓨터소프트웨어공학과)
  • Received : 2019.06.30
  • Accepted : 2019.08.11
  • Published : 2019.08.01
⟨ Previous Next ⟩

Abstract

Against advanced image-related crimes, a high level of digital forensic methods is required. However, feature-based methods are difficult to respond to new device features by utilizing human-designed features, and deep learning-based methods should improve accuracy. This paper proposes a deep learning model to identify camera models based on DenseNet, the recent technology in the deep learning model field. To extract camera sensor features, a HPF feature extraction filter was applied. For camera model identification, we modified the number of hierarchical iterations and eliminated the Bottleneck layer and compression processing used to reduce computation. The proposed model was analyzed using the Dresden database and achieved an accuracy of 99.65% for 14 camera models. We achieved higher accuracy than previous studies and overcome their disadvantages with low accuracy for the same manufacturer.

영상 관련 범죄가 증가하고 고도화됨에 따라서 고수준의 디지털 포렌식 기술이 요구된다. 그러나 기존의 특징 기반 기술은 인간이 고안한 특징을 활용함으로서 새로운 기기 특징에 쉽게 대응하기 어렵고, 딥러닝 기반 기술은 정확도 향상이 요구된다. 본 논문에서는 딥러닝 모델 분야의 최신 기술인 DenseNet을 기반으로 카메라 모델 판별을 위한 딥러닝 모델을 제안한다. 카메라의 센서 특징을 획득하기 위해 HPF 특징 추출 필터를 적용하였고, 카메라 판별에 적합하도록 기존 DenseNet에서 계층 반복 수를 조정하였다. 또한 연산량을 줄이기 위한 Bottleneck layer와 압축 연산 처리를 제거하였다. 제안한 모델을 Dresden 데이터베이스를 사용하여 성능 분석을 하였고, 14개 카메라 모델에 대해 99.65%의 정확도를 달성하였다. 기존 연구들보다 높은 정확도를 달성하였으며 기존에 동일한 제조사에서 정확도가 낮아지는 단점을 극복하였다.

Keywords

References

  1. H. Y. Lee, "Imaging Device Identification using Sensor Pattern Noise Based on Wiener Filtering", The Transactions of the Korean Institute of Electrical Engineers, Vol. 65, No. 12, pp. 2153- 2158, Sep. 2016. https://doi.org/10.5370/KIEE.2016.65.12.2153
  2. G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, "Densely Connected Convolutional Networks", Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp. 4700-4708, Jul. 2017.
  3. Dresden Image Database, http://forensics.inf.tudresden.de/ddimgdb/ [accessed: Jun. 26, 2019]
  4. S. Bayram, H. T. Sencar, and N. Memon, "Source camera identification based on CFA interpolation", Proc. of IEEE Int. Conf. on Image Processing, Genova, Italy, Vol. 3, pp. 69-72, Sep. 2005.
  5. K. S. Choi, E. Y. Lam, and K. K. Y. Wong, "Automatic source camera identification using the intrinsic lens radial distortion", Optics Express, Vol. 14, No. 24, pp. 11551-11565, Nov. 2006. https://doi.org/10.1364/OE.14.011551
  6. Y. Tomioka and H. Kitazawa, "Digital camera identification based on the clustered pattern noise of image sensors", Proc. of IEEE Int. Conf. on Multimedia and Expo, Barcelona, Spain, pp. 1-4, Jul. 2011.
  7. J. Lukas, J. Fridrich, and M. Goljan, "Digital camera identification from sensor pattern noise", IEEE Trans. on Information Forensics Security, Vol. 1, No. 2, pp. 205-214, Jun. 2006. https://doi.org/10.1109/TIFS.2006.873602
  8. A. Jeyalakshmi and D. R. Chitra, "Source Camera Identification using Image Features", International Journal of Applied Engineering Research, Vol. 13, No. 1, pp. 490-504, Jan. 2018.
  9. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems, Vol. 25, No. 2, pp. 1097-1105, Jan. 2012.
  10. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, and A. Rabinovich, "Going deeper with convolutions", Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 1-9, Jun. 2015.
  11. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition", Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770-778, Jun. 2016.
  12. L. Baroffio, L. Bondi, P. Bestagini, and S. Tubaro, "Camera identification with deep convolutional networks", arXiv preprint arXiv:1603. 01068, Mar. 2016.
  13. A. Tuama, F. Comby, and M. Chaumont, "Camera model identification with the use of deep convolutional neural networks", Proc. of IEEE Int. Workshop on Information Forensics and Security, Abu Dhabi, United Arab Emirates, pp. 1-6, Dec. 2016.
  14. A. Kuzin, A. Fattakhov, I. Kibardin, V. I. Iglovikov, and R. Dautov, "Camera Model Identification Using Convolutional Neural Networks", Proc. of IEEE Int. Conf. on Big Data, Seattle, USA, pp. 3107-3110, Dec. 2018.
  15. A. M. Rafi, T. I. Tonmoy, R. Hoque, and M. Hasan, "RemNet: Remnant Convolutional Neural Network for Camera Model Identification", arXiv preprint arXiv:1902.00694, Feb. 2019.
  16. U. Kamal, A. M. Rafi, R. Hoque, S. Das, A. Abrar, and M. Hasan, "Application of DenseNet in Camera Model Identification and Post-processing Detection", arXiv preprint arXiv:1809.00576, Sep. 2018.
  17. H. Yao, T. Qiao, M. Xu, and N. Zheng, "Robust multi-classifier for camera model identification based on convolution neural network", IEEE Access, Vol. 6, pp. 24973-24982, May 2018. https://doi.org/10.1109/ACCESS.2018.2832066
  18. D. Freire-Obregon, F. Narducci, S. Barra, and M. rillon-Santana, "Deep learning for source camera identification on mobile devices", Pattern Recognition Letters, Available online 9, Jan. 2018.
  19. M. Darvish Morshedi Hosseini, and M. Goljan, "Camera Identification from HDR Images", Proc. of ACM Workshop on Information Hiding and Multimedia Security, pp. 69-76, Jul. 2019.
  20. C. Meij and Z. Geradts, "Source camera identification using Photo Response Non-Uniformity on WhatsApp", Digital Investigation, Vol. 24, pp. 142-154, Mar. 2018. https://doi.org/10.1016/j.diin.2018.02.005