IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Dual Branched Copy-Move Forgery Detection Network Using Rotation Invariant Energy in Wavelet Domain

웨이블릿 영역에서 회전 불변 에너지 특징을 이용한 이중 브랜치 복사-이동 조작 검출 네트워크

  • Received : 2022.10.13
  • Accepted : 2022.11.26
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

Keywords

Acknowledgement

본 논문은 부산대학교 기본연구지원사업 (2년)에 의하여 연구되었음.

References

  1. S. Teerakanok, T. Uehara, "Copy-move Forgery Detection: A State-of-the-art Technical Review and Analysis," IEEE Access., Vol. 7, pp. 40500-40568, 2019.
  2. R. Thakur, R. Rohilla, "Recent Advances in Digital Image Manipulation Detection Techniques: A Brief Review," Forensic Sci. Int., Vol. 312, 110311, 2020.
  3. G. Lynch, F. Y. Shih, H. Y. Liao, "An Efficient Expanding Block Algorithm for Image Copy-move Forgery Detection," Inf. Sci., Vol. 239, pp. 2253-265, 2013.
  4. Y. Sun, R. Ni, Y. Zhao, "Nonoverlapping Blocks Based Copy-move Forgery Detection," Secur. Commun. Netw., Vol. 2018, Article ID 1301289, 2018.
  5. Y. Gao, T. Gao, L. Fan, Q. Yang, "A Robust Detection Algorithm for Copy-move Forgery in Digital Images," Forensic Sci. Int., Vol. 214, No. 1, pp. 33-43, 2011. https://doi.org/10.1016/j.forsciint.2011.07.015
  6. Y. Li, "Image Copy-move Forgery Detection Based on Polar Cosine Transform and Approximate Nearest Neighbor Searching," Forensic Sci. Int., Vol. 224, No. 1-3, pp. 59-67, 2013. https://doi.org/10.1016/j.forsciint.2012.10.031
  7. R. Dixit, R. Nakar, "Copy-move Forgery Detection Utilizing Fourier-Mellin Transform Log-polar Features," J. Electron. Imaging., Vol. 27, No. 2, 023007, 2018.
  8. K. M. Hosny, H. M. Hamza, N. A. Lashin, "Copy-move Forgery Detection of Duplicated Objects Using Accurate PCET Moments and Morphological Operators," Imag. Sci. J., Vol. 66, No. 6, pp. 330-345, 2018. https://doi.org/10.1080/13682199.2018.1461345
  9. M. H. Alkawas, G. Sulong, T. Sabas, A. Rehman, "Detection of Copy-move Image Forgery Based on Discrete Cosine Transform," Neural Comput. Appl., Vol. 30, pp. 183-192, 2016. https://doi.org/10.1007/s00521-016-2663-3
  10. T. Mahmood, A. Irtaza, Z. Mehmood, M. T. Mahmood, "Copy-move Forgery Detection Through Stationary Wavelets and Local Binary Pattern Variance for Forensic Analysis in Digital Images," Forensic Sci. Int., Vol. 279, pp. 8-21, 2017. https://doi.org/10.1016/j.forsciint.2017.07.037
  11. M. Zandi, A. Mahmoudi-Aznaveh, A. Talebpour, "Iterative Copy-move Forgery Detection Based on a New Interest Point Detector," IEEE Trans. Inf. Forensics Secur., Vol. 11, No. 11, pp. 2499-2512, 2016. https://doi.org/10.1109/TIFS.2016.2585118
  12. C. M. Pun, J. L. Chung, "A Two-stage Localization for Copy-move Forgery Detection," Inf. Sci., Vol. 463-464, pp. 33-55, 2018. https://doi.org/10.1016/j.ins.2018.06.040
  13. X. Pan and S. Lyu, "Region Duplication Detection Using Image Feature Matching," IEEE Trans. Inf. Forensics Secur., Vol. 5, No. 4, pp. 857-867, Dec. 2010. https://doi.org/10.1109/TIFS.2010.2078506
  14. I. Amerini, L. Ballan, R. Caldelli, A. Del Bimbo, G. Serra, "A SIFT-based Forensic Method for Copy- move Attack Detection and Transformation Recovery," IEEE Trans. Inf. Forensics Secur., Vol. 6, No. 3, pp. 1099-1110, 2011. https://doi.org/10.1109/TIFS.2011.2129512
  15. V. Christlein, C. Riess, J. Jordan, C. Riess, E. Angelopoulou, "An Evaluation of Popular Copy-move Forgery Detection Approaches," IEEE Trans. Inf. Forensics Secur., Vol. 7, No. 6, pp. 1841-1854, 2012. https://doi.org/10.1109/TIFS.2012.2218597
  16. C. M. Pun, X. C. Yuan, X. L. Bi, "Image Forgery Detection Using Adaptive Oversegmentation and Feature Point Matching," IEEE Trans. Inf. Foren. Secur., Vol. 10, No. 8, pp. 1705-1716, 2015. https://doi.org/10.1109/TIFS.2015.2423261
  17. J. Y. Park, T. A. Kang, I. K. Eom, "Copy-move Forgery Detection Using Scale Invariant Feature and Reduced Local Binary Pattern Histogram," Symmetry, Vol. 12, No. 4, 492, 2020.
  18. G. Jin, X. Wan, "An Improved Method for SIFT-based Copy-move Forgery Detection Using Non-maximum Value Suppression and Optimized J-Linkage," Signal Process. Image Commun., Vol. 57, pp. 113-125, 2017. https://doi.org/10.1016/j.image.2017.05.010
  19. D. M. Uliyan, H. A. Jalab, A. W. A. Wahab, S. Sadeghi, "Image Region Duplication Forgery Detection based on Angular Radial Partitioning and Harris Key-points," Symmetry, Vol. 8, No. 7, pp. 62, 2016.
  20. N. B. A. Warif, A. W. A. Wahab, M. Y. I. Idris, R. Salleh, F. Othman, "SIFT-symmetry: A Robust Detection Method for Copy-move Forgery with Refection Attack," J. Vis. Commun. Image Represent., Vol. 46, pp. 219-232, 2017. https://doi.org/10.1016/j.jvcir.2017.04.004
  21. Y. Wu, W. Abd-Almageed, P. Natarajan, ''BusterNet: Detecting Copy-move Image Forgery with Source/target Localization," Proceedings of the European Conference on Computer Vision, Munich, Germany, pp. 168-184, 2018.
  22. J. L. Zhong, C. M. Pun, "An End-to-end Dense-InceptionNet for Image Copy-move Forgery Detection," IEEE Trans. Inf. Forensics Secur., Vol. 15, pp. 2134-2146, 2020. https://doi.org/10.1109/tifs.2019.2957693
  23. B. Chen, W. Tan, G. Coatrieux, Y. Zheng, Y. Q. Shi, "A Serial Image Copy-move Forgery Localization Scheme with Source/target Distinguishment," IEEE Trans. Multimed., Vol. 23, pp. 3506-3517, 2021.
  24. K. Simonyan, A. Zisserman, "Very Deep Convolutional Networks for Large-scale Image Recognition," Proceedings of 3rd International Conference on Learning Representations, pp. 1-14, 2015.
  25. L. Chen, G. Papandreou, I. Kokkinos, K. Murphy, A. L. Yuille, "DeepLab: Semantic Image SSegmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs," IEEE Trans. Pattern Anal. Mach. Intell., Vol. 40, No. 4, pp. 834-848, 2018. https://doi.org/10.1109/TPAMI.2017.2699184
  26. S. I. Lee, J. Y. Park, I. K. Eom, "CNN-based Copy-move Forgery Detection Using Rotation-invariant Wavelet Feature," IEEE Access, Vol. 10, pp. 106217-106229, 2022. https://doi.org/10.1109/ACCESS.2022.3212069
  27. G. Cheng, J. Han, P. Zhou, D. Xu, "Learning Rotation-invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection," IEEE Trans. Image Process., Vol. 28, No. 1, pp. 265-278, 2019. https://doi.org/10.1109/tip.2018.2867198
  28. S. Woo, J. Park, J.-Y. Lee, I. S. Kweon, ''CBAM: Convolutional Block Attention Module," Proceedings of European Conference on Computer Vision, pp. 3-19, 2018.