On parameterization of block based copy-move forgery detection techniques

Abstract

With high increase in cyber-crime along with continuous development in multimedia processing and editing technologies, the credibility of digital images is highly at stake in the present day. Digital images act as the major source of legal evidence in various domains such as media, broadcast and legal industries. Hence any form of illegal modifications to them is intolerable. Recently a lot of researchers have focused on detection and control of digital image forgeries. However the literature lacks a standard way of evaluating and comparing the efficiencies of diverse forgery detection techniques. In this paper we propose a standard platform for estimating the efficiencies of state-of-the-art digital image forgery detection techniques. In this work we have dealt with a specific class of digital image forgery: the Copy-Move forgery, which is one of most prevalent forms of attack on digital images. We have compared and analyzed different copy-move forgery detection techniques using the proposed parameters. Our results prove the efficiency of the proposed parameterization and help to select the most suitable scheme according to the user's requirements.