Multimedia Tools and Applications

, Volume 75, Issue 6, pp 3221–3233 | Cite as

Copy-move forgery detection based on scaled ORB

Article

Abstract

To solve the problem of the false matching and low robustness in detecting copy-move forgeries, a new method was proposed in this study. It involves the following steps: first, establish a Gaussian scale space; second, extract the orientated FAST key points and the ORB features in each scale space; thirdly, revert the coordinates of the orientated FAST key points to the original image and match the ORB features between every two different key points using the hamming distance; finally, remove the false matched key points using the RANSAC algorithm and then detect the resulting copy-move regions. The experimental results indicate that the new algorithm is effective for geometric transformation, such as scaling and rotation, and exhibits high robustness even when an image is distorted by Gaussian blur, Gaussian white noise and JPEG recompression; the new algorithm even has great detection on the type of hiding object forgery.

Keywords

Image blind identification Copy-move forgery Scale space ORB feature RANSAC 

References

  1. 1.
    Amerini I, Ballan L, Caldelli R et al (2011) A SIFT-based forensic method for copy–move attack detection and transformation recovery. IEEE Trans Inf Forensic Secur 6:1099–1110. doi:10.1109/TIFS.2011.2129512 CrossRefGoogle Scholar
  2. 2.
    Bayram S, Sencar HT, Memon N (2009) An efficient and robust method for detecting copy-move forgery. ICASSP:1053–1056. doi:10.1109/ICASSP.2009.4959768
  3. 3.
    Calonder M, Lepetit V, Strecha C et al. (2010) Brief: binary robust independent elementary features. ECCV:778–792. doi: 10.1007/978-3-642-15561-1_56
  4. 4.
    Davarzani R, Yaghmaie K, Mozaffari S et al (2013) Copy-move forgery detection using multiresolution local binary patterns. Forensic Sci Int 231:61–72. doi:10.1016/j.forsciint.2013.04.023 CrossRefGoogle Scholar
  5. 5.
    Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381–395. doi:10.1145/358669.358692 MathSciNetCrossRefGoogle Scholar
  6. 6.
    Fridrich J, Soukal BD, Lukáš AJ (2003) Detection of copy-move forgery in digital images. Proc Digit Forensic Res WorkGoogle Scholar
  7. 7.
    Heinly J, Dunn E, Frahm JM (2012) Comparative evaluation of binary features. ECCV:759–773. doi: 10.1007/978-3-642-33709-3_54
  8. 8.
    Hu J, Zhang H, Gao Q (2011) An improved lexicographical sort algorithm of copy-move forgery detection. ICNDC:23–27. doi: 10.1109/ICNDC.2011.12
  9. 9.
    Huang H, Guo W, Zhang Y(2008) Detection of copy-move forgery in digital images using SIFT algorithm. PACIIA: 1241–1245. doi: 10.1109/PACIIA.2008.240
  10. 10.
    Leutenegger S, Chli M, Siegwart RY (2011) BRISK: binary robust invariant scalable keypoints. ICCV:2548–2555. doi: 10.1109/ICCV.2011.6126542
  11. 11.
    Liu G, Wang J, Lian S (2011) A passive image authentication scheme for detecting region-duplication forgery with rotation. J Netw Comput Appl 34:1557–1565. doi:10.1016/j.jnca.2010.09.001 CrossRefGoogle Scholar
  12. 12.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91–110. doi:10.1023/B:VISI.0000029664.99615.94 CrossRefGoogle Scholar
  13. 13.
    Luo W, Huang J, Qiu G (2007) Robust detection of region-duplication forgery in digital image. ICPR 4:746–749. doi:10.1109/ICPR.2006.1003 Google Scholar
  14. 14.
    Mahdian B, Saic S (2007) Detection of copy–move forgery using a method based on blur moment invariants. Forensic Sci Int 171:180–189. doi:10.1016/j.forsciint.2006.11.002 CrossRefGoogle Scholar
  15. 15.
    Muhammad G, Hussain M, Bebis G (2012) Passive copy move image forgery detection using undecimated dyadic wavelet transform. Digit Investig 9:49–57. doi:10.1016/j.diin.2012.04.004 CrossRefGoogle Scholar
  16. 16.
    Popescu AC, Farid H (2004) Exposing digital forgeries by detecting duplicated image regions. Dissertation, Dartmouth CollegeGoogle Scholar
  17. 17.
    Rosin PL (1999) Measuring corner properties. Comput Vis Image Underst 73:291–307. doi:10.1006/cviu.1998.0719 CrossRefGoogle Scholar
  18. 18.
    Rosten E, Drummond T (2005) Fusing points and lines for high performance tracking. ICCV: 1508–1515. doi: 10.1109/ICCV.2005.104
  19. 19.
    Rosten E, Drummond T (2006) Machine learning for high-speed corner detection. ECCV:430–443. doi: 10.1007/11744023_34
  20. 20.
    Rublee E, Rabaud V, Konolige K (2011) ORB: an efficient alternative to SIFT or SURF. ICCV:2564–2571. doi: 10.1109/ICCV.2011.6126544
  21. 21.
    Ryu SJ, Lee MJ, Lee HK (2010) Detection of copy-rotate-move forgery using Zernike moments. Inf Hiding:51–65. doi: 10.1007/978-3-642-16435-4_5
  22. 22.
    Wang X, Zhang X, Li Z et al. (2011) A DWT-DCT based passive forensics method for copy-move attacks. MINES:304–308. doi: 10.1109/MINES.2011.98
  23. 23.
    Xu B, Wang J, Liu G (2010) Image copy-move forgery detection based on SURF. MINES:889–892. doi: 10.1109/MINES.2010.189
  24. 24.
    Yao H, Qiao T, Tang Z, et al. (2011) Detecting copy-move forgery using non-negative matrix factorization. MINES:591–594. doi: 10.1109/MINES.2011.104
  25. 25.
    Zhang T, Wang R (2009) Copy-move forgery detection based on SVD in digital image. ICISP:1–5. doi: 10.1109/CISP.2009.5301325

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Jilin UniversityChangchunChina
  2. 2.College of Computer Science and TechnologyJilin UniversityChangchunChina

Personalised recommendations