Authors: D. Vaishnavi; T.S. Subashini
Addresses: Department of Computer Science and Engineering, Faculty of Engineering and Technology, Annamalai University, Tamil Nadu, India ' Department of Computer Science and Engineering, Faculty of Engineering and Technology, Annamalai University, Tamil Nadu, India
Abstract: The multimedia data such as digital images are essential to expose the evidence. There are numerous, image editing software through which the original images can be intentionally manipulated or forged for mishandling purposes. It is very difficult to discover the forgery by visually analysing it. Specifically, the copy move forgery is extremely challenging to expose the forged region. In this paper, contrast context histogram (CCH) features are used to effectively detect the copy move forgery and k-means clustering algorithm to segregate the key points of copy move forged regions. The disparity map is created using sum of absolute difference to localise these regions. The comparative study was carried out and the performances reveal that the proposed system is better than the existing methods.
Keywords: passive forensics; copy move forgery detection; contrast context histogram; CCH features; disparity maps; RANSAC; image forgery; multimedia; digital images; k-means clustering; image security.
International Journal of Electronic Security and Digital Forensics, 2015 Vol.7 No.3, pp.278 - 289
Received: 08 Oct 2014
Accepted: 02 Mar 2015
Published online: 04 Jul 2015 *