Copy-move forgery detection based on multifractals
- 119 Downloads
Digital images and video are the basic media for communication nowadays. They are used as authenticated proofs or corroboratory evidence in different areas like: forensic studies, law enforcement, journalism and others. With development of software for editing digital images, it has become very easy to change image content, add or remove important information or even to make one image combining multiple images. Thus, the development of methods for such change detection has become very important. One of the most common methods is copy-move forgery detection (CMFD). Methods of this type include change detection that occur by copying a part of an image and pasting it to another location within the image. We propose new method for detection of such changes using certain multifractal parameters as characteristic features, as well as common statistical parameters. Before the analysis, images are divided into non-overlapping blocks of fixed dimensions. For each block, the characteristic features are calculated. In order to classify observed blocks, we used metaheuristic method and proposed new semi-metric function for similarity analysis between blocks. Simulation shows that the proposed method provides good results in terms of precision and recall, with low computational complexity.
KeywordsImage forensics CMFD (copy-move forgery detection) Multifractal spectrum Hölder exponent Metaheuristic method Semi-metric
This work has been supported by the Serbian Ministry of Science, Grant nos. III044006, III44009 and TR32023.
- 2.Alkawaz MH, Sulong G, Saba T, Rehman A (2016) Detection of copy-move image forgery based on discrete cosine transform. Neural Comput & Applic:1–10. https://doi.org/10.1007/s00521-016-2663-3
- 6.Chou CL, Lee JC (2017) Copy-Move Forgery Detection Based on Local Gabor Wavelets Patterns. In: International Conference on Security with Intelligent Computing and Big-data Services (pp. 47-56). https://doi.org/10.1007/978-3-319-76451-1_5
- 7.CoMoFoD database, available at: http://www.vcl.fer.hr/comofod. Accessed March 2018
- 11.Glisovic N, Davidovic T, Bojovic N, Kenzevic N Statistical and Mathematical Methods for Solving the Problem of Clustering of Station Data When Data Is Incomplete, Conference: XXXV Symposium on New Technologies in Postal and Telecommunication Vehicles, PosTel 2017. Traffic Faculty, BelgradeGoogle Scholar
- 12.Glisovic N, Davidovic T, Raskovic M (2017) Clustering when missing data by using the variable neighborhood search, (in serbian). In: Proc. SYM-OP-IS 2017, pages 158-163, ZlatiborGoogle Scholar
- 16.Image Manipulation Dataset, available at: https://www5.cs.fau.de/research/data/image-manipulation/. Accessed April 2018
- 24.Mladenović N, Sörensen K, Souza M (eds) (2018) Special issue on “Advances in Variable Neighborhood Search”. Int Trans Oper Res 25(1):427–427Google Scholar
- 25.Mohsen J, Mohsen E-M (2016) Blind Detection of Region Duplication Forgery Using Fractal Coding and Feature Matching. J Forensic Sci 61(3). https://doi.org/10.1111/1556-4029.13108
- 27.Reljin I, Reljin B, Pavlovic I, Rakočevic I (2000). Multifractal analysis of gray-scale images. In: Electrotechnical Conference, 2000. MELECON 2000. 10th Mediterranean (Vol. 2, pp. 490-493). IEEEGoogle Scholar
- 29.Soni B, Das PK, Thounaojam DM (2018) Dual System for Copy-move Forgery Detection using Block-based LBP-HF and FWHT Features. Eng Lett 26(1). https://doi.org/10.1109/TIFS.2010.2051666