Rotation and scale invariant upsampled log-polar fourier descriptor for copy-move forgery detection

Digital image forgery is becoming increasingly popular with the rapid progress of digital media editing tools. Copy-move forgery (CMF) is one of the most common methods of digital image forgery. For CMF detection (CMFD), we propose an upsampled log-polar Fourier (ULPF) descriptor that is robust to several geometric transformations including rotation, scaling, sheering, and reflection. We first describe the theoretical background of the ULPF representation. Then, we propose a feature extraction algorithm that can extract rotation and scale invariant features from the ULPF representation. In addition, we analyze the common CMFD processing pipeline and improve a part of processing pipeline to efficiently handle various types of tampering attacks. In our simulation, we present comparative results between the proposed feature descriptor and state-of-the-art ones with proven performance guarantees.