Consistency features and fuzzy-based segmentation for shadow and reflection detection in digital image forgery

Research Paper
  • 79 Downloads

Abstract

Advances in photo editing software have made it possible to generate visually convincing photo-graphic forgeries which have been increased tremendously in recent years. In order to alleviate the problem of image forgery, a handful of techniques have been presented in the literature to detect forgery either in shadow or reflection. This paper aims to develop a technique to detect the image forgery either in shadow or reflection using features enabled neural network. The proposed technique of image forgery detection contains three important steps, like segmentation, feature extraction and detection. In segmentation, shadow points and reflection points are identified using map-based segmentation and FCM clustering. Then, feature points from the shadow points and reflective parts are extracted by considering texture consistency and strength consistency using LVP operator. The final step of forgery detection is performed using the feed forward neural network, where a new algorithm called ABCLM is developed for training of neural network weights. The performance is analyzed with four existing algorithms using measures such as accuracy and MSE. From the analysis, we understand that the proposed technique obtained the maximum accuracy of 80.49%.

Keywords

image forensics forgery detection shadow reflection texture neural network 

References

  1. 1.
    Muhammad G, Hussain M, Bebis G. Passive copy move image forgery detection using undecimated dyadic wavelet transform. Digit Investig, 2012, 9: 49–57CrossRefGoogle Scholar
  2. 2.
    Muhammad G, Hussain M, Khawaji K, et al. Blind copy move image forgery detection using dyadic undecimated wavelet transform. In: Proceedings of 17th International Conference on Digital Signal Processing (DSP), Corfu, 2011. 1–6Google Scholar
  3. 3.
    Birajdar G K, Mankar V H. Digital image forgery detection using passive techniques: a survey. Digit Investig, 2013, 10: 226–245CrossRefGoogle Scholar
  4. 4.
    Kee E, O’Brien J F, Farid H. Exposing photo manipulation from shading and shadows. ACM Trans Graph, 2014, 33: 165CrossRefGoogle Scholar
  5. 5.
    Zhang W, Cao X C, Zhang J W, et al. Detecting photographic composites using shadows. In: Proceedings of the IEEE International Conference on Multimedia and Expo, New York, 2009. 1042–1045Google Scholar
  6. 6.
    Liu Q G, Cao X C, Deng C, et al. Identifying image composites through shadow matte consistency. IEEE Trans Inform Forens Secur, 2011, 6: 1111–1122CrossRefGoogle Scholar
  7. 7.
    Yang B, Sun X M, Chen X Y, et al. Exposing photographic splicing by detecting the inconsistencies in shadows. Computer J, 2015, 58: 588–600CrossRefGoogle Scholar
  8. 8.
    Ge H Y, Malik H. Exposing image forgery using inconsistent reflection vanishing point. In: Proceedings of International Conference on Audio, Language and Image Processing, Shanghai, 2014. 282–286Google Scholar
  9. 9.
    Ke Y Z, Qin F, Min W D, et al. Exposing image forgery by detecting consistency of shadow. Sci World J, 2014, 2014: 364501CrossRefGoogle Scholar
  10. 10.
    Bayram S, Sencar H T, Memon N. An efficient and robust method for detecting copy-move forgery. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Washington DC: IEEE Computer Society, 2009. 1053–1056Google Scholar
  11. 11.
    Popescu A C, Farid H. Exposing digital forgeries by detecting traces of re-sampling. IEEE Trans Signal Process, 2005, 53: 758–767CrossRefGoogle Scholar
  12. 12.
    Wang W, Dong J, Tan T N. Effective image splicing detection based on image chroma. In: Proceedings of IEEE International Conference on Image Processing, Cairo, 2009. 1257–1260Google Scholar
  13. 13.
    O’Brien J F, Farid H. Exposing photo manipulation with inconsistent reflections. ACM Trans Graph, 2012, 31: 4Google Scholar
  14. 14.
    Rufenacht D, Fredembach C, Susstrunk S. Automatic and accurate shadow detection using near-infrared information. IEEE Trans Patt Anal Mach Intell, 2013, 36: 1672–1678CrossRefGoogle Scholar
  15. 15.
    Fan K-C, Hung T-Y. A novel local pattern descriptor—local vector pattern in high-order derivative space for face recognition. IEEE Trans Image Process, 2014, 23: 2877–2891MathSciNetCrossRefGoogle Scholar
  16. 16.
    Hagan M T, Menhaj M. Training feed-forward networks with the Marquardt algorithm. IEEE Trans Neural Netw, 1994, 5: 989–993CrossRefGoogle Scholar
  17. 17.
    Karaboga D, Basturk B. A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J Global Optim, 2007, 9: 459–471MathSciNetCrossRefMATHGoogle Scholar
  18. 18.
    Kee E, O’Brien J F, Farid H. Exposing photo manipulation with inconsistent shadows. ACM Trans Graph, 2013, 32: 28CrossRefGoogle Scholar
  19. 19.
    Cao X C, Zhao H D, Wang C, et al. Image composite authentication using a single shadow observation. Sci China Inf Sci, 2015, 58: 092110CrossRefGoogle Scholar
  20. 20.
    Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern, 1979, 9: 62–66CrossRefGoogle Scholar
  21. 21.
    Bezdek J C. Pattern Recognition with Fuzzy Objective Function Algorithms. New York: Plenum Press, 1981CrossRefMATHGoogle Scholar
  22. 22.
    Auer P, Burgsteiner H, Maass W. A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Netw, 2008, 21: 786–795CrossRefMATHGoogle Scholar

Copyright information

© Science China Press and Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  1. 1.St. Peter’s Institute of Higher Education and ResearchChennaiIndia
  2. 2.Dr. M.G.R Educational and Research Institute UniversityChennaiIndia

Personalised recommendations