DOI QR코드

DOI QR Code

Forged Color Region Detection Using Color Pattern Decomposition and Hypothesis Test

컬러 패턴의 분해와 가설검정을 이용한 컬러 조작 영역 검출

  • Seo, Jun Ryung (Dept. Electronics Eng., Pusan National University) ;
  • Eom, Il Kyu (Dept. Electronics Eng., Pusan National University)
  • Received : 2015.03.16
  • Accepted : 2015.07.01
  • Published : 2015.07.25

Abstract

In this paper, we present a new method that can detect forged color region using color pattern decomposition and hypothesis testing approach. On the basis of the fact that the variance of the interpolated pixel is smaller than that of the original pixel, we use a statistical test method to judge the statistical inconsistency of variance. For this, we calculate the variance adopting a color pattern decomposition according to the demosaicking pattern. In addition, we apply high-pass filtering to enlarge the difference between the variances of original and interpolated pixel. Through experimental simulations, we can see that our proposed method can effectively detect forged color regions and shows superior detection performance compared to the conventional method.

본 논문에서는 컬러 패턴의 분해와 가설검정 기법을 이용하여 영상에서 조작된 컬러의 영역을 검출하는 새로운 방법을 제시한다. 디모자이킹으로 보간된 화소는 원 화소보다 적은 분산을 가진다는 것에 착안하여, 통계적 검정을 이용하여 분산의 불일치성을 판단하는 방법을 사용한다. 이를 위해, 컬러 패턴을 각각 디모자이킹 패턴에 따라 분해하는 방법을 도입하여 분산을 계산한다. 또한 보간된 화소와 원 화소의 분산의 차이를 크게 하기 위하여 고역통과 필터링을 적용한다. 실험 결과를 통하여 제안 방법이 컬러 조작 영역을 찾는데 매우 유효하며 기존 방법과 비교하여 우수한 검출 성능을 보이는 것을 확인 할 수 있었다.

Keywords

References

  1. H. Farid, "A picture tells a thousand lies", New Scientist, vol. 2411, pp. 38-41, 2003.
  2. H. Farid, "A survey of image forgery detection," IEEE Signal Processing Magazine, vol. 26, no. 2, pp. 16-25, 2009. https://doi.org/10.1109/MSP.2008.931079
  3. A. Piva, "An overviwe on image forensics," ISRN Signal Processisng, vol. 2013, Article ID 496701, pp. 1-22, 2013.
  4. B. Mahdian, S. Saic, "A bibliography on blind methods for identifying image forgery," Signal Processing: Image Communication, vol. 25, no. 6, pp. 389-399, 2010. https://doi.org/10.1016/j.image.2010.05.003
  5. G. K. Birajdar, V. H. Mankar, "Digital image forgery detection using passive techniques: A survey," Digital Investigation, vol. 10, no. 3, pp. 226-245, 2013. https://doi.org/10.1016/j.diin.2013.04.007
  6. Sang Hwan Moon, Jong Goo Han, Yong Ho Moon, Il Kyu Eom, "Color Image Splicing Detection using Benford's Law and color Difference," Journal of IEIE, vol.51, No.5, pp.160-167, 2014.
  7. Jong Goo Han, Tae Hee Park, Il Kyu Eom, "Efficient Markov Feature Extraction Method for Image Splicing Detection," Journal of IEIE, vol.51, No.9, pp.111-118, 2014.
  8. C. H. Choi, H. Y. Lee, and H. K. Lee, "Estimation of color modification in digital images by CFA pattern change," Forensic science international, vol. 226, pp. 94-105, 2013. https://doi.org/10.1016/j.forsciint.2012.12.014
  9. B. E. Bayer, "Color imaging array," U. S. Patent, No. 3,971,065. Jul, 1976.
  10. A. C. and H. Farid, "Exposing digital forgeries in color filter array interpolated images," IEEE Transactions on Signal Processing, vol. 53, no. 10, pp. 3948-3959, 2005. https://doi.org/10.1109/TSP.2005.855406
  11. H. Cao and A. C. Kot. "Accurate detection of demosaicing regularity for digital image forensics," IEEE Transactions on Information Forensics and Security, vol. 4, no. 4, pp. 899-910, 2009. https://doi.org/10.1109/TIFS.2009.2033749
  12. G. E. P Box, "Non-normality and tests on variances," vol. 40, no. 3/4, pp. 18-335, 1953.
  13. T. Gloe, R. Bohme, The 'Dresden Image Database' for benchmarking digital image forensics, in: Proceedings of the 25th Symposium On Applied Computing (ACMSAC 2010), vol. 2, 2010, pp. 1585-1591.