Detection of Copy-Move Forgery Using Hybrid approach of DCT and BRISK

With the advancement in the image editing tools day by day and their increased usage, image forgery has become a serious problem. Copy-move forgery (CMF) is one of the most common image tampering techniques being used. There are many post-processing techniques applied on forged images such as scaling, blurring, JPEG compression and rotation to hide forgery traces. Single image might contain multiple forged regions. In this paper, we have proposed a hybrid method involving DCT (Discrete cosine Transform) and BRISK (Binary Robust Invariant Scalable Keypoints) features, for copy-move forgery detection. DCT is a feature set that would provide invariance to blurring, while BRISK would provide invariance to rotation and scaling. Features are extracted using DCT and BRISK keypoints and descriptors. For matching BRISK descriptors FLANN matcher is used, and for removing the false matches Euclidean distance-based clustering technique is used. The experimental result shows that our method is not only robust to blurring but also robust to transformations like rotation and scaling. It is also able to detect multiple forged regions. The method is tested on CoMoFoD dataset. Results of the proposed work are also compared with two standard approaches mentioned in experiment and result section.