Enhanced Fiilltterr-based SIFT Apprroach fforr Copy-Move Forrgerry Dettecttiion

Image forgeries are applied to give the digital images othermeanings or to deceive the viewers. Image forgeries appear inmany cases such as judges in courts, cybercrimes, military andintelligence deception, or defamation of important characters.There are many different types of image forgeries such as copymove forgery, image retouching, image splicing, image morphing,and image resampling. Copy move forgery is the widest type andeasy to apply between all digital image forgeries. Scale InvariantFeatures Transform (SIFT) algorithm is used strongly to detectcopy move forgeries due to its efficiency in digital image analysis.SIFT algorithm is extracting image features, which are invariant togeometrical transformations such as scaling, translation, androtation. These features are used in performing the matchingbetween different views of a scene or an object. This paperenhances the efficiency of using SIFT algorithm in detecting copymove forgery by two ways. Firstly, it enhances the image itself byapplying different types of digital filters to reinforce the imagefeatures giving the ability to detect forgeries. Butterworth low-passfilter, a high-pass filter, and the combination of them are appliedto this task. Secondly, the matching strategy is adapted based ona new thresholding approach to increase the true positive rateand decrease the false positive rate. Experimental results showthat the proposed approach gives better results compared withtraditional copy-move detection approaches. In addition, it gives better stability and reliability to different copy-move forgery conditions.