DOI QR코드

DOI QR Code

Forensic Classification of Median Filtering by Hough Transform of Digital Image

디지털 영상의 허프 변환에 의한 미디언 필터링 포렌식 분류

  • RHEE, Kang Hyeon (Chosun University, College of Electronics and Information Eng., Dept. of Electronics Eng)
  • 이강현 (조선대학교 전자정보공과대학 전자공학과)
  • Received : 2017.03.09
  • Accepted : 2017.04.07
  • Published : 2017.05.25

Abstract

In the distribution of digital image, the median filtering is used for a forgery. This paper proposed the algorithm of a image forensics detection for the classification of median filtering. For the solution of this grave problem, the feature vector is composed of 42-Dim. The detected quantity 32, 64 and 128 of forgery image edges, respectively, which are processed by the Hough transform, then it extracted from the start-end point coordinates of the Hough Lines. Also, the Hough Peaks of the Angle-Distance plane are extracted. Subsequently, both of the feature vectors are composed of the proposed scheme. The defined 42-Dim. feature vector is trained in SVM (Support Vector Machine) classifier for the MF classification of the forged images. The experimental results of the proposed MF detection algorithm is compared between the 10-Dim. MFR and the 686-Dim. SPAM. It confirmed that the MF forensic classification ratio of the evaluated performance is 99% above with the whole test image types: the unaltered, the average filtering ($3{\times}3$), the JPEG (QF=90 and 70)) compression, the Gaussian filtered ($3{\times}3$ and $5{\times}5$) images, respectively.

본 논문에서는 디지털 영상의 배포에서, 위 변조에 사용되는 미디언 필터링 (Median Filtering : MF)을 분류하는 포렌식 검출 알고리즘을 제안한다. 이러한 문제를 해결하기 위한 특징벡터는 영상의 에지 검출량 정보 32, 64, 128에 대한 허프변환(Hough Transform)에 의하여, 각 허프라인 (Hough Line)의 양끝 좌표값과 Angle-Distance 좌표상의 허프픽크치 (Hough Peaks)를 조합하여 42-Dim.으로 구성하였다. 변조된 영상들 중에서 미디언 필터링을 분류하는 검출기는 SVM (Support Vector Machine)에서 특징벡터를 학습하여 구현되었다. 제안된 미디언 필터링 검출 알고리즘은 특징벡터의 길이가 10-Dim.의 MFR (Median Filtering Residual) 스킴 및 686-Dim.의 SPAM (Subtractive Pixel Adjacency Matrix) 스킴과 비교하여 원영상, 평균필터링 ($3{\times}3$), JPEG (QF=90, 70) 압축, 가우시안 필터링 ($3{\times}3$, $5{\times}5$) 영상 모두에서 미디언 필터링의 포렌식 분류율이 99% 이상의 성능을 확인하였다.

Keywords

References

  1. Kang Hyeon RHEE, "Image Forensic Decision Algorithm using Edge Energy Information of Forgery Image," Journal of The Institute of Electronics and Information Engineers, Vol. 51, No. 3, pp. 75-81, March 2014. https://doi.org/10.5573/ieie.2014.51.3.075
  2. Hany Farid, "Image forgery detection," IEEE Signal Processing Magazine, Vol. 26, Issue: 2, pp.16-25, 2009. https://doi.org/10.1109/MSP.2008.931079
  3. 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
  4. Tomas Pevny, "Steganalysis by Subtractive Pixel Adjacency Matrix," Information Forensics and Security, IEEE Transactions on, Vol. 5, pp. 215-224, 2010. https://doi.org/10.1109/TIFS.2010.2045842
  5. Duda, R. O., P. E. Hart, "Use of the Hough Transformation to Detect Lines and Curves in Pictures," Comm. ACM, Vol. 15, pp. 11-15, January 1972. https://doi.org/10.1145/361237.361242
  6. Kang Hyeon RHEE, "Forensic Detection of Median Filtering by Hough Transform of Digital Image," The 9th IEEE GCC Conference & Exhibition (Bahrain), May 2017.
  7. Kang Hyeon RHEE, "Downscaling Forgery Detection using Pixel Value's Gradients of Digital Image," Journal of The Institute of Electronics and Information Engineers, Vol. 53, No. 2, pp. 47-52, Feb. 2016. https://doi.org/10.5573/IEIE.2016.53.2.047
  8. G. Schaefer and M. Stich, "UCID - An uncompressed colour image database," in Proc. SPIE, Storage and Retrieval Methods and Applications for Multimedia, San Jose, USA, 2004, pp. 472-480
  9. V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995.
  10. Kang Hyeon RHEE, "Median filtering detection using variation of neighboring line pairs for image forensics," SPIE, Journal of Electronic Imaging, 25(5), 2016.