Copy Move Forgery detection and localisation robust to rotation using block based Discrete Cosine Transform and eigenvalues

The contemporary era faces a widespread issue with digital image forgery, posing a significant challenge due to its ease and the broad reach enabled by high-speed internet. This manipulation of images carries substantial socio-political implications globally. Hence, robust digital image forensic methods are critical for detecting such forgeries. This article presents an innovative algorithm specifically designed to detect and locate copy-move duplication within digital images. By utilizing the Discrete Cosine Transform and eigenvalues as distinguishing features, the algorithm precisely identifies and pinpoints replicated image regions from overlapping pixel blocks. Uniquely, another cumulative DCT feature enhances the algorithm’s ability to discern duplicated regions, even when subjected to post-processing rotation attacks. Experiments using various datasets demonstrate that this method outperforms avant-garde techniques in detecting and localising forgeries, showcasing promising results. This approach contributes significantly to the field of digital image forensics, providing a valuable tool for identifying and localising manipulated content.