Open Access Open Access  Restricted Access Subscription or Fee Access

Duplicated Region Detection Using Robust Features

Jiang Wen

Abstract


Region duplication is a common form of image forgery in which a part of digital image is copied and moved to another part of the same image in order to conceal some important objects. At present, most of the detection algorithm is based on the pixel block matching or the match transforms domain coefficients. However, the detection method becomes invalid when the duplicated regions suffer post processing, such as geometrical or illumination distortions. This paper aims to design a novel scheme that is robust to noise pollution and geometrical distortions of duplicated regions, by using speed-up robust feature (SURF) key-points, which are insensitive to geometrical and illumination distortions. Firstly, SURF key-points are found out; secondly, they are matched with each other. With the matched key-point pairs, one can estimate the affine transform matrix which is critical to locate the tempered area; finally, the tempered area can be detected by morphological operation. Experiment results show that the proposed method outperforms existing methods. The proposed algorithm can detect duplicated regions even the tempered image suffering from the post-processing, including rotate, scale, noise contamination, and jpeg-compression.

Keywords


Image forensics, region duplication, affine-transform, Speeded up Robust Feature.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.