Robust evidence detection of copy-rotate-move forgery in image based on singular value decomposition

Abstract

Region Copy-Move forgery, in which a part of the image is copied and then pasted to another part of the same image. Some important goals and sensitive objects can be hidden imperceptibly; this forgery is at the rather important position in a variety of forensic technology research. But the literatures published merely are confined without geometric distortion. And some algorithms focus on the special forgery's model. In order to improve the accuracy of the current algorithms, a new detection is proposed by constructing the circles rather than the traditional ways which were based on the square. The seven characterizes are constructed according to singular value decomposition. Using main rotation angle based on the radial moment and the proportion of constraint remove the error mark. Finally the dictionary-ordering method is applied to save the time-consuming. The experiment shows that this newly characteristic can locate the area where was tampered. © 2012 Springer-Verlag.