Xiu-Li Bi, Chi-Man Pun, Xiao-Chen Yuan
This paper proposes an adaptive over-segmentation meth-od for image copy-move forgery detection. Firstly, the Adaptive Over-Segmentation algorithm is proposed to adaptively segment the host image into non-overlapping and irregular blocks. Then the feature points are extracted and matched with each other to locate the labeled feature points which can approximately indicate the suspected forgery regions. Finally the labeled feature points are processed and the morphological operation is applied to generate the detected forgery regions. Experimental results indicate the good performance of the proposed copy-move forgery detection.