What is the best algorithm for copy-move forgery detection (CMFD)?

A copy-move forgery is created by copying and pasting content within the same image, and potentially postprocessing it. In recent years, the detection of copy-move forgeries has become one of the most actively researched topics in blind image forensics. A considerable number of different algorithms have been proposed focusing on different types of postprocessed copies.

In our paper "An Evaluation of Popular Copy-Move Forgery Detection Approaches" (TIFS 2012), we aim to answer which copy-move forgery detection features and which processing pipeline performs best in various postprocessing scenarios. We achieve this by casting existing algorithms in a common pipeline and examining the 15 most prominent feature sets. We also created a challenging real-world copy-move dataset, and a software framework for systematic image manipulation.

Quick links to

• the paper
• the dataset
• the code

If you want to use the dataset or the code, please cite our paper "An Evaluation of Popular Copy-Move Forgery Detection Approaches"; Vincent Christlein, Christian Riess, Johannes Jordan, Corinna Riess, Elli Angelopoulou. In: IEEE Transactions on Information Forensics and Security (TIFS) 2012, accepted for publication.

Note that the presented code is research quality, we take no liability for it. However, we are glad if you have suggestions for improvements.