A Copy-Move Detection Algorithm Using Binary Gradient Contours
Nowadays copy-move attack is one of the most obvious ways of digital image forgery in order to hide the information contained in images. Copy-move process consists of copying the fragment from one place of an image, changing it and pasting it to another p
- PDF / 1,696,040 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 11 Downloads / 215 Views
Samara National Research University (SNRU), Samara, Russia [email protected], [email protected] 2 Image Processing Systems Institute of the Russian Academy of Sciences (IPSI RAS), Samara, Russia
Abstract. Nowadays copy-move attack is one of the most obvious ways of digital image forgery in order to hide the information contained in images. Copy-move process consists of copying the fragment from one place of an image, changing it and pasting it to another place of the same image. However, only a few existing studies reached high detection accuracy for a narrow range of transform parameters. In this paper, we propose a copy-move detection algorithm that uses features based on binary gradient contours that are robust to contrast enhancement, additive noise and JPEG compression. The proposed solution showed high detection accuracy and the results are supported by conducted experiments for wide ranges of transform parameters. A comparison of features based on binary gradient contours and based on various forms of local binary patterns showed a significant 20–30 % difference in detection accuracy, corresponding to an improvement with the proposed solution. Keywords: Copy-move detection Transformed duplicate binary pattern Binary gradient contours k-d tree
Forgery Local
1 Introduction Nowadays, digital images play an important role in different spheres of human society. At present, digital image usage is great. They are often used to prove various facts or events. However, we cannot be sure that these data has not been altered by people with malicious intent. Statistics indicate that users uploaded over 300 million digital images a day using Facebook social network in 2015 [1]. It should be noted that a huge number of web applications (Instagram, Twitter, Flickr, etc.) process a comparable to Facebook traffic of digital images. It is evident that such a huge amount of data will not be missed by attackers, because people firstly analyze information as it is, and then express criticism over it. Digital images may be easily changed by attackers to hide data and provide forgeries to the end users. Created forgeries can be used in compromising form and cause serious political and economic consequences if fake data is not detected. That is the problem that led to a rapid development of forgery detection algorithms. One of the most frequently used image forgery method is copying a fragment from one place of an image and paste it to another place of the same image. Such attacks are © Springer International Publishing Switzerland 2016 A. Campilho and F. Karray (Eds.): ICIAR 2016, LNCS 9730, pp. 349–357, 2016. DOI: 10.1007/978-3-319-41501-7_40
350
A. Kuznetsov and V. Myasnikov
called copy-move attacks, and the copied regions are called duplicates. Different transforms can be applied to a duplicate before paste: affine transform, contrast enhancement, additive noise, and others. In this paper we detect duplicates transformed using contrast enhancement, additive noise and JPEG compression. Currently, there is
Data Loading...
