Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

Image Forensic Decision Algorithm using Edge Energy Information of Forgery Image

위·변조 영상의 에지 에너지 정보를 이용한 영상 포렌식 판정 알고리즘

  • Rhee, Kang Hyeon (Chosun University, College of Electronics and Information Eng., Dept. of Electronics Eng.)
  • 이강현 (조선대학교 전자정보공과대학 전자공학과)
  • Received : 2014.01.16
  • Published : 2014.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

In a distribution of the digital image, there is a serious problem that is distributed an illegal forgery image by pirates. For the problem solution, this paper proposes an image forensic decision algorithm using an edge energy information of forgery image. The algorithm uses SA (Streaking Artifacts) and SPAM (Subtractive Pixel Adjacency Matrix) to extract the edge energy informations of original image according to JPEG compression rate(QF=90, 70, 50 and 30) and the query image. And then it decides the forge whether or not by comparing the edge informations between the original and query image each other. According to each threshold in TCJCR (Threshold by Combination of JPEG Compression Ratios), the matching of the edge informations of original and query image is excused. Through the matching experiments, TP (True Positive) and FN (False Negative) is 87.2% and 13.8% respectively. Thus, the minimum average decision error is 0.1349. Also, it is confirmed that the performed class evaluation of the proposed algorithm is 'Excellent(A)' because of the AUROC (Area Under Receiver Operating Characteristic) curve is 0.9388 by sensitivity and 1-specificity.

디지털 영상의 배포에서, 저작권 침해자에 의해 영상이 불법으로 위 변조되어 유통되는 심각한 문제가 대두되어 있다. 이러한 문제를 해결하기 위하여, 본 논문에서는 위 변조된 디지털 영상의 에지 에너지 정보를 이용한 영상 포렌식 판정 알고리즘을 제안한다. 제안된 알고리즘은 SA (Streaking Artifacts)와 SPAM (Subtractive Pixel Adjacency Matrix)을 이용하여, 원 영상의 JPEG 압축률 (QF=90, 70, 50, 30)에 따른 에지정보와 질의영상의 에지정보를 추출하고, 이를 각각 비교하여 위 변조 여부를 판정한다. 원 영상과 질의영상의 에지정보 매칭은 JPEG 압축률 조합의 임계치 (TCJCR : Threshold by Combination of JPEG Compression Ratios)에 따라 이루어진다. 실험을 통하여, TP (True Positive)와 FN (False Negative)은 87.2%와 13.8%이며, 산출된 최소평균 판정 에러는 0.1349이다. 그리고 제안된 알고리즘의 성능평가에서 민감도 (Sensitivity)와 1-특이도(1-Specificity)의 AUROC (Area Under Receiver Operating Characteristic) 커브 면적은 0.9388로 'Excellent(A)' 등급임을 확인하였다.

Keywords

References

  1. T. Pevny, P. Bas, and J. Fridrich, "Steganalysis by subtractive pixel adjacency matrix," in MM&Sec'09, Proceedings of the Multimedia and Security Workshop 2009, September 7-8, 2009, Princeton, NJ, USA, pp. 75-84, ACM Press, (New York, NY, USA), 2009.
  2. M. Kirchner and J. Fridrich, "On detection of median filtering in digital images," in Proc. SPIE, Electronic Imaging, Media Forensics and Security II, vol. 7541, San Jose, CA, pp. 1-12, Jan. 2010.
  3. G. Cao, Y. Zhao, R. Ni, L. Yu, and H. Tian, "Forensic detection ofmedian filtering in digital images," in Proc. 2010 IEEE Int. Conf. Multimedia and EXPO, pp. 89-94, Jul. 2010.
  4. Xiangui Kang, Matthew C. Stamm, Anjie Peng, and K. J. Ray Liu, "Robust Median Filtering Forensics Using an Autoregressive Model," IEEE Trans. on Information Forensics and Security, vol. 8, no. 9, pp. 1456-1468, Sept. 2013. https://doi.org/10.1109/TIFS.2013.2273394
  5. H. Yuan, "Blind forensics of median filtering in digital images," IEEE Trans. Inf. Forensics Security, vol. 6, no. 4, pp. 1335-1345, Dec. 2011. https://doi.org/10.1109/TIFS.2011.2161761
  6. C. Chen, J. Ni, R. Huang, and J. Huang, "Blind median filtering detection using statistics in difference domain," in Proc. of Information Hiding 2012, May 2012.
  7. A. C. Popescu and H. Farid, "Exposing digital forgeries by detecting traces of resampling," IEEE Trans. Signal Process, vol. 53, no. 2, pp. 758-767, Feb. 2005. https://doi.org/10.1109/TSP.2004.839932
  8. Y. T. Kao, H. J. Lin, C. W. Wang, and Y. C. Pai, "Effective detection for linear up-sampling by a factor of fraction," IEEE Trans. Image Process., vol. 21, no. 8, pp. 3443-3453, Aug. 2012. https://doi.org/10.1109/TIP.2012.2191562
  9. R. Neelamani, R. de Queiroz, Z. Fan, S. Dash, and R. Baraniuk, "JPEG compression history estimation for color images," IEEE Trans. Image Process., vol. 15, no. 6, pp. 1365-1378, Jun. 2006. https://doi.org/10.1109/TIP.2005.864171
  10. A. C. Bovik, "Streaking in median filtered images," IEEE Trans. on Acoust., Speech and Signal Processing, vol. 35, no. 4, pp. 493-503, Apr. 1987 https://doi.org/10.1109/TASSP.1987.1165153
  11. http://vision.cs.aston.ac.uk/datasets/UCID/ucid.html
  12. T. Pevny and J. Fridrich, "Detection of double-compression in JPEG images for applications in steganography," IEEE Trans. Inf. Forensics Security, vol. 3, no. 2, pp. 247-258, Jun. 2008. https://doi.org/10.1109/TIFS.2008.922456
  13. Matthias Kirchner and Rainer Bhme, "Tamper hiding: Defeating image forensics.," in Information Hiding'07, pp. 326-341, Jun. 2007.
  14. M. Fontani and M. Barni, "Hiding Traces of Median Filtering in Digital Images," 20th European Signal Processing Conference (EUSIPCO 2012), pp. 1239-1243, Aug. 2012.
  15. Kang Hyein RHEE, "A Design on the Multimedia Fingerprinting code based on Feature Point for Forensic Marking," IEEK, Journal-CI 48(4), pp. 27-34, 2011.7.
  16. Kang Hyein RHEE, "An Implementation on the XOR-ACC of Multimedia Fingerprinting using Neural Network," IEEK, Journal-CI 48(6), pp. 1-8, 2011.11

Cited by

  1. Median Filtering Detection using Latent Growth Modeling vol.52, pp.1, 2015, https://doi.org/10.5573/ieie.2015.52.1.061