One of the most common image tampering techniques is copy-move; in this technique, one or more parts of the image are copied and pasted in another area of the image. Recently, various methods have been proposed for copy-move detection; however, many of these techniques are not robust to additional changes like geometric transformation, and they are failed to be useful for detecting small copied areas. In this paper, a new method based on point descriptors which are derived from the integration of textural feature-based Weber law and statistical features of the image is presented. In this proposed approach, modified multiscale version of Weber local descriptor is presented to make the method robust versus geometric transformation and detect small copied areas. The results of the experiments showed that our method can detect small copied areas and copy-move tampered images which are influenced by rotation, scaling, noise addition, compression, blurring, and mirroring.
Keywords: Weber local descriptor; clustering; copy-move detection; feature extraction; forensic science; tamper detection.
© 2015 American Academy of Forensic Sciences.