IMAGING SCIENCE JOURNAL, vol.64, no.4, pp.215-225, 2016 (SCI-Expanded)
Copy move forgery is one of the most widely used tampering techniques to hide undesirable objects in a scene. Existing techniques to detect such tampering aim to improve the robustness of the methods. A robust method based on the colour moments and colour layout descriptors (CLD) is proposed in this paper. The method divides the image into overlapping blocks. First colour moments of the blocks are used to group similar blocks into clusters. Blocks from the tampered regions are similar and going to be mapped into the same cluster. Thus, search for copied and moved regions in clusters to detect forgery can be done by separate threads. CLD is used to extract block features, which makes the method more robust to post-processing operations. Experimental results indicate that the proposed method can detect copy move forgery even if additive white Gaussian noise, JPEG compression or Gaussian blurring is used after forgery.