Multi-scale Analysis Strategies in PRNU-based Tampering Localization

Paweł Korus and Jiwu Huang

IEEE Transactions on Information Forensics and Security, Vol. 12, Issue 4, 2017

2017-tifs-multiscale-prnu.pdf (5 MB)

10.1109/TIFS.2016.2636089

https://github.com/pkorus/multiscale-prnu

Abstract

Accurate unsupervised tampering localization is one of the most challenging problems in digital image forensics. In this study, we consider photo response non-uniformity (PRNU) analysis and focus on the detection of small forgeries. For this purpose, we adopt a recently proposed paradigm of multi-scale analysis and discuss various strategies for its implementation. Firstly, we consider a multi-scale fusion approach which involves combination of multiple candidate tampering probability maps into a single, more reliable decision map. The candidate maps are obtained with sliding windows of various sizes and thus allow to exploit the benefits of both small and large-scale analysis. We extend this approach by introducing modulated threshold drift and content-dependent neighborhood interactions, leading to improved localization performance with superior shape representation and easier detection of small forgeries. We also discuss two novel alternative strategies: a segmentation-guided approach which contracts the decision statistic to a central segment within each analysis window; and an adaptive-window approach which dynamically chooses analysis window size for each location in the image. We perform extensive experimental evaluation on both synthetic and realistic forgeries and discuss in detail practical aspects of parameter selection. Our evaluation shows that multi-scale analysis leads to significant performance improvement compared with the commonly used single-scale approach. The proposed multi-scale fusion strategy delivers stable results with consistent improvement in various test scenarios.