IMPROVEMENT OF THE METHOD FOR IDENTIFYING OF CLONING RESULTS IN A DIGITAL IMAGE
DOI:
https://doi.org/10.24025/2306-4412.3.2019.177317Keywords:
digital image, integrity violation, clone, prototype, geometric transformations, singular spectrum, matrix of minimal block differencesAbstract
Cloning remains one of the most common tools used for unauthorized changes to digital images. Cloning is implemented in all modern graphic editors. Many experts in the field of information security are engaged in solving the problem of cloning detection, but this task has no final solution to date. A modification of the method for identifying cloning results in a digital image is proposed in the paper. The effectiveness of this method exceeds the efficiency of modern analogues. It remains effective when the cloned image is subjected to additional disturbing influences. These disturbing influences do not differ for the clone and prototype. Also, the method is effective when the size of the clone / prototype is small. The purpose of the modification of the method is to ensure its effectiveness under the conditions of certain geometric transformations to which the clone is subjected. These transformations are: reflection relative to the vertical and/or horizontal axis, rotation through an angle multiple of 90°, reflection relative to the diagonal (main, secondary) of the corresponding matrix. In this paper, the principle of constructing a matrix of minimal block differences is changing. This matrix is mapped to a digital image. It is the main subject of research in the method. The element of the matrix of minimal block differences reflects the smallest difference of a particular block from any other block of the image. The difference between the blocks is calculated as the difference of their singular spectra. The singular spectrum of the matrix does not change during the geometric transformation. Advanced method has high efficiency. A value of TRP = 100 % indicates that when the method is running, skip-ping of cloned images does not occur. The improved method is also effective in identifying several clones that correspond to one prototype. Several clones experience different geometric transfor-mations.References
B. L. Shivakumar, and S. S. Baboo, "Detecting copymove forgery in digital images: а survey and analysis of current methods", Global Journal of Computer Science and Technology, 10 (7), pp. 61-65, 2010.
R. Singh, and M. Kaur, "Copy-move tampering detection techniques: а review", International Journal of Applied Engineering Research, 11 (5), pp. 3610-3615, 2016.
E. Silva, T. Carvalho, A. Ferreira, and A. Rocha, "Going deeper into copy-move forgery detection: exploring image telltales via multi-scale analysis and voting processes", J. Vis. Commun. Image Represent, 29, pp. 16-32, 2015.
S. Grigorenko, "Development of method for detection of cloning in digital images under additional disturbing influences", Legal, Regulatory and Metrological Support Information Security System in Ukraine, 1 (31), pp. 85-98, 2016 [in Ukrainian].
A. A. Kobozeva, I. I. Bobok, and S. M. Grygorenko, "Method for detecting of clone areas in a digital image under conditions of additional attacks", Journal of Signal Processing Systems, 2019. [Online].Available: https://doi.org/10.1007/s11265-019-01449-6
A. A. Kobozieva, I. I. Bobok, "Theoretical bases for the improvement of the method of detection of the results of cloning in a digital image in conditions of additional perturbation actions", Modern Special Technics, 1, pp. 29-39, 2018 [in Ukrainian].
J. W. Demmel, Applied numerical linear algebra. Moscow: Mir, 2001 [in Russian].
A. A. Kobozeva, V. A. Khoroshko, Analysis of information protection. Kyiv: GUIKT, 2009 [in Russian].
F. R. Gantmacher, Theory of matrices. 5th еd. Moscow: Fismatlit, 2004 [in Russian].
I. Amerini, L. Ballan, R. Caldelli, A. del Bimbo, L. del Tongo, and G. Serra, "Copy-move forgery detection and localization by means of robust clustering with J-linkage", Signal Processing, 28 (6), pp. 659-669, 2013.
Pan, X., Lyu, S. (2010). "Detecting image region duplication using SIFT features", in Proc. 2010 IEEE Internat. Conf. on Acoustics, Speech and Signal Processing (ICASSP-2010). Dallas, pp. 1706-1709.
I. Amerini, L. Ballan, R.Caldelli, A. del Bimbo, and G. Serra, "A SIFT-based forensic method for copy move attack detection and transformation recovery", IEEE Transactions on Information Forensics and Security, 6 (3), pp. 1099-1110, 2011.
P. Mishra, N. Mishra, S. Sharma, and R. Patel, "Region duplication forgery detection technique based on SURF and HAC", The Scientific World Journal, 6, pp. 1-8, 2013.
M. F. Hashmi, V. Anand, and A. G. Keskar, "Copy-move image forgery detection using efficient and robust method combining undecimated wavelet transform and scale invariant feature transform", in AASRI Conf. on Circuit and Signal Processing, 2014, pp. 84-91.
Diaa M. Uliyan, Hamid A. Jalab, and Wahab Ainuddin W. Abdul, "Copy move image forgery detection using Hessian and center symmetric local binary pattern", Proc. IEEE Conf. on Open Systems (ICOS). Bandar Melaka, 2015, pp. 7-11.
Diaa M. Uliyan, Hamid A. Jalab, Wahab Ainuddin W. Abdul, and Somayeh Sadeghi, "Image region duplication forgery detection based on angular radial partitioning and Harris key-points", Symmetry, 8 (7), pp. 56-65, 2016.
Downloads
Published
How to Cite
Issue
Section
URN
License
Copyright (c) 2020 Володимир Олексійович Хорошко, Іван Ігорович Бобок The authors who publish in this journal agree to the following terms:The authors reserve the right to authorship of their work and give the journal the right to first publish this work under the terms of the Creative Commons Attribution License CC BY-NC, which allows other persons to freely distribute published work with a mandatory reference to authors of the original work and the first publication of the work in this journal.
Authors have the right to conclude separate additional agreements for the non-exclusive distribution of the paper in the form in which it was published by this journal (for example, posting work in electronic repository or publishing as part of a monograph), provided that the link to the first publication in this journal is maintained.
The journal policy allows and encourages authors to post on the Internet (for example, in repositories of institutions or on personal websites) the manuscript of work, both before the submission of this manuscript to the editorial staff, and during its editorial work, as it contributes to the emergence of productive scientific discussion and positively affects the efficiency and dynamics of published work citation (see The Effect of Open Access).
