A novel framework for image forgery localization
This addresses the challenge of detecting image manipulations for forensic applications, but it appears incremental as it combines existing tools.
The authors tackled the problem of localizing forged regions in images by proposing a framework that fuses three different tools based on sensor noise, patch-matching, and machine learning, resulting in often very good localization accuracy and sometimes valuable clues for visual scrutiny in preliminary experiments.
Image forgery localization is a very active and open research field for the difficulty to handle the large variety of manipulations a malicious user can perform by means of more and more sophisticated image editing tools. Here, we propose a localization framework based on the fusion of three very different tools, based, respectively, on sensor noise, patch-matching, and machine learning. The binary masks provided by these tools are finally fused based on some suitable reliability indexes. According to preliminary experiments on the training set, the proposed framework provides often a very good localization accuracy and sometimes valuable clues for visual scrutiny.