방송공학회논문지 (Journal of Broadcast Engineering)

  • 제24권6호
  • /
  • Pages.1134-1142
  • /
  • 2019
  • /
  • 1226-7953(pISSN)
  • /
  • 2287-9137(eISSN)
한국방송∙미디어공학회 (The Korean Institute of Broadcast and Media Engineers)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 기술 기반 HEVC로 압축된 영상의 이중 압축 검출 기술

Deep Learning based HEVC Double Compression Detection

  • 우딘 쿠툽 (한국항공대학교 항공전자정보공학부) ;
  • 양윤모 (한국항공대학교 항공전자정보공학부) ;
  • 오병태 (한국항공대학교 항공전자정보공학부)
  • Uddin, Kutub (Korea Aerospace University, School of Electronics and Information Engineering) ;
  • Yang, Yoonmo (Korea Aerospace University, School of Electronics and Information Engineering) ;
  • Oh, Byung Tae (Korea Aerospace University, School of Electronics and Information Engineering)
  • 투고 : 2019.09.04
  • 심사 : 2019.10.22
  • 발행 : 2019.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

영상의 이중 압축 검출은 영상의 위조여부를 판단하는 한가지 효과적인 방식이다. 이러한 이중 압축 검출 기술을 바탕으로 HEVC로 압축된 영상의 진위 여부를 판단하는 다양한 종류의 기존 기술들이 소개되었지만, 동일한 압축 환경에서 이중 압축된 영상의 진위 여부를 검출하는 것은 상당히 어려운 일로 여겨지고 있다. 본 논문에서는 동일 압축 환경에서 HEVC의 이중압축 여부를 판단하는 기술로서, Intra모드로 압축된 영상의 분할 정보를 이용하여 판단하는 방식을 제안한다. Coding Unit (CU)와 Transform Unit (TU)의 분할 정보로부터 통계적 특징과 딥러닝 네트워크 기반의 특징을 우선 추출하고, softmax단에서 추출된 특징들을 통합하여 이중 압축 여부를 판단하는 기술을 제안한다. 실험결과를 통해서 제안하고 있는 기술이 WVGA 영상과 HD 영상에서 각각 87.5%와 84.1%의 정확도를 가지며 효과적으로 검출한다는 것을 보여준다,

Detection of double compression is one of the most efficient ways of remarking the validity of videos. Many methods have been introduced to detect HEVC double compression with different coding parameters. However, HEVC double compression detection under the same coding environments is still a challenging task in video forensic. In this paper, we introduce a novel method based on the frame partitioning information in intra prediction mode for detecting double compression in with the same coding environments. We propose to extract statistical feature and Deep Convolution Neural Network (DCNN) feature from the difference of partitioning picture including Coding Unit (CU) and Transform Unit (TU) information. Finally, a softmax layer is integrated to perform the classification of the videos into single and double compression by combing the statistical and the DCNN features. Experimental results show the effectiveness of the statistical and the DCNN features with an average accuracy of 87.5% for WVGA and 84.1% for HD dataset.

키워드

참고문헌

  1. J. H. Hong, Y. Yang, and B.T. Oh. "Detection of frame deletion in HEVC-coded video in the compressed domain." Digital Investigation, 2019.
  2. S. Milani, M. Fontani, P. Bestagini, M. Barni, A. Piva, M. Tagliasacchi, and S. Tubaro. "An overview on video forensics." APSIPA Transactions on Signal and Information Processing, 1, 1-18, 2012.
  3. F. Huang, J. Huang, and Y. Q. Shi. "Detecting double JPEG compression with the same quantization matrix." IEEE Transactions on Information Forensics and Security, 5(4), 848-856, 2010. https://doi.org/10.1109/TIFS.2010.2072921
  4. J. Yang, J. Xie, G. Zhu, S. Kwong, and Y. Q. Shi. "An effective method for detecting double JPEG compression with the same quantization matrix." IEEE Transactions on Information Forensics and Security, 9(11), 1933-1942, 2014. https://doi.org/10.1109/TIFS.2014.2359368
  5. X. Huang, S. Wang, and G. Liu. "Detecting double JPEG compression with same quantization matrix based on dense CNN feature." 25th IEEE International Conference on Image Processing (ICIP), 3813-3817, 2018.
  6. P. Peng, T. Sun, X. Jiang, K. Xu, B. Liu, and Y. Q. Shi. "Detection of double JPEG compression with the same quantization matrix based on convolutional neural networks." IEEE Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 717-721, 2018.
  7. T. Sun, W. Wang, and X. Jiang. "Exposing video forgeries by detecting MPEG double compression." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1389-1392, 2012.
  8. J. A. Aghamaleki, and A. Behrad. "Detecting double compressed MPEG videos with the same quantization matrix and synchronized group of pictures structure." Journal of Electronic Imaging, 27(1), 013031, 2018.
  9. X. Jiang, W. Wang, T. Sun, Y. Q. Shi, and S. Wang. "Detection of double compression in MPEG-4 videos based on Markov statistics." IEEE Signal Processing Letters, 20(5), 447-450, 2013. https://doi.org/10.1109/LSP.2013.2251632
  10. H. Liu, S. Li, and S. Bian. "Detecting frame deletion in H. 264 video." International Conference on Information Security Practice and Experience, Springer, 262-270, 2014.
  11. H. Yao, S. Song, C. Qin, Z. Tang, and X. Liu. "Detection of double-compressed H.264/AVC video incorporating the features of the string of data bits and skip macroblocks." Symmetry, 9(12), 313, 2017. https://doi.org/10.3390/sym9120313
  12. D. Liao, R. Yang, H. Liu, J. Li, and J. Huang. "Double H. 264/AVC compression detection using quantized nonzero AC coefficients." Media Watermarking, Security, and Forensics III, International Society for Optics and Photonics, 7880, 78800Q, 2011.
  13. Q. Xu, T. Sun, X. Jiang, and Y. Dong. "HEVC double compression detection based on SN-PUPM feature." International Workshop on Digital Watermarking, Springer, Cham, 3-17, 2017.
  14. Q. Li, R. Wang, and D. Xu. "Detection of double compression in HEVC videos based on TU size and quantized DCT coefficients." IET Information Security, 13(1), 1-6, 2018. https://doi.org/10.1049/iet-ifs.2017.0555
  15. L. Yu, Y. Yang, Z. Li, Z. Zhang, and G. Cao. "HEVC double compression detection under different bitrates based on TU partition type." EURASIP Journal on Image and Video Processing, 2019(1), 67, 2019. https://doi.org/10.1186/s13640-019-0468-x
  16. M. Huang, R. Wang, J. Xu, D. Xu, and Q. Li. "Detection of double compression for HEVC videos based on the co-occurrence matrix of DCT coefficients." International Workshop on Digital Watermarking. Springer, Cham, 9569, 61-71, 2015.
  17. Z. H. Li, R. S. Jia, Z. Z. Zhang, X. Y. Liang, and J. W. Wang. "Double HEVC compression detection with different bitrates based on co-occurrence matrix of PU types and DCT coefficients." ITM Web of Conferences, EDP Sciences, 12, 01020, 2017. https://doi.org/10.1051/itmconf/20171201020
  18. X. Jiang, P. He, T. Sun, and R. Wang. "Detection of double compressed HEVC videos using GOP-based PU type statistics." IEEE Access, 7, 95352-95363, 2019.
  19. I. K. Kim, J. Min, T. Lee, W. J. Han, and J. H. Park. "Block partitioning structure in the HEVC standard." IEEE transactions on circuits and systems for video technology, 22(12), 1697-1706, 2012. https://doi.org/10.1109/TCSVT.2012.2223011
  20. Z. Huang, F. Huang, and J. Huang. "Detection of double compression with the same bit rate in MPEG-2 videos." IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP), 306-309, 2014.
  21. X. Jiang, P. He, T. Sun, F. Xie, and S. Wang. "Detection of double compression with the same coding parameters based on quality degradation mechanism analysis." IEEE Transactions on Information Forensics and Security, 13(1), 170-185, 2018. https://doi.org/10.1109/TIFS.2017.2745687
  22. X. Jiang, Q. Xu, T. Sun, B. Li, and P. He. "Detection of HEVC double compression with the same coding parameters based on analysis of intra coding quality degradation process." IEEE Transactions on Information Forensics and Security, 2019.
  23. A. A. Elrowayati, M. F. L. Abdullah, A. A. Manaf, and A. S. Alfagi. "Tampering detection of double-compression with the same quantization parameter in HEVC video streams." 7th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 174-179, 2017.
  24. ftp://ftp.ivc.polytech.univ-nantes.fr/IRCCyN_IVC_1080i_Database/1080i_Videos