A Copy-Move Detection Algorithm Based on Geometric Local Binary Pattern
An obvious way of digital image forgery is a copy-move attack. It is quite simple to carry out to hide important information in an image. Copy-move process contains three main steps: copy the fragment from one place of an image, transform it by some means and paste to another place of the same image. A lot of papers on development of copy-move detection algorithms exist nowadays though the achieved results are far from perfect, so they are frequently improved. In this paper, it is proposed a new copy-move detection algorithm based on geometric local binary patterns (GLBP). GLBP features are robust to contrast enhancement, additive Gaussian noise, JPEG compression, affine transform. Another advantage of these features is low computational complexity. Conducted experiments compare GLBP-based features with features based on other forms of local binary patterns. The proposed solution showed high precision and recall values during experimental research for wide ranges of transform parameters. Thus, it showed a meaningful improvement in detection accuracy.
KeywordsForgery detection Copy-move Geometric local binary pattern GLBP feature Transform invariant
- 3.Bayram, S., Sencar, H.T., Memon, N.: An efficient and robust method for detecting copy-move forgery. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1053–1056 (2009)Google Scholar
- 10.Kang, X., Wei, S.: Identifying tampered regions using singular value decomposition in digital image forensics. In: Proceedings of the 2008 IEEE International Conference on Computer Science and Software Engineering, pp. 926–930 (2008)Google Scholar
- 12.Fridrich, J., Soukal, D., Lukáš, J.: Detection of copy-move forgery in digital images. In: Proceedings of the Digital Forensic Research Workshop. Citeseer (2003)Google Scholar
- 15.Orjuela Vargas, S.A., Yañez Puentes, J.P., Philips, W.: The geometric local textural patterns (GLTP). In: Brahnam, S., Jain, L., Nanni, L., Lumini, A. (eds.) Local Binary Patterns: New Variants and Applications. Studies in Computational Intelligence, vol. 506. Springer, Heidelberg (2014). doi: 10.1007/978-3-642-39289-4_4
- 17.Arasteh, S., Hung, C.-C.: Color and texture image segmentation using uniform local binary patterns. Mach. Graph. Vis. 15(3–4), 265–274 (2006)Google Scholar