Robust Copy-move Forgery Detection through Invariant Moment Features

The proposed scheme uses the invariant features extracted from each block to detect the copy-move forgery regions in a digital image. In the proposed scheme, an image is first divided into overlapping blocks. Then, seven invariant moments of the maximum circle area in each block are calculated as moment features. Mean and variance of these seven moment features, as second feature set, are acquired for block comparison to reduce computation time. Thus, the proposed scheme outperforms previous schemes. The copy-move forgery regions can be found by matching the detected blocks with relative distance calculation. Experimental results show that the adopted moment features are efficient for detecting rotational or flipped duplicated regions.