PhotoHolmes: a Python library for forgery detection in digital images
This work addresses the need for reproducible and accessible tools in digital image forgery detection, primarily benefiting researchers and practitioners in computer vision and forensics, though it is incremental as it builds on existing methods.
The authors introduced PhotoHolmes, an open-source Python library that facilitates forgery detection in digital images by providing implementations of state-of-the-art methods, dataset integration, and evaluation tools, enabling easy benchmarking and accessibility for the community.
In this paper, we introduce PhotoHolmes, an open-source Python library designed to easily run and benchmark forgery detection methods on digital images. The library includes implementations of popular and state-of-the-art methods, dataset integration tools, and evaluation metrics. Utilizing the Benchmark tool in PhotoHolmes, users can effortlessly compare various methods. This facilitates an accurate and reproducible comparison between their own methods and those in the existing literature. Furthermore, PhotoHolmes includes a command-line interface (CLI) to easily run the methods implemented in the library on any suspicious image. As such, image forgery methods become more accessible to the community. The library has been built with extensibility and modularity in mind, which makes adding new methods, datasets and metrics to the library a straightforward process. The source code is available at https://github.com/photoholmes/photoholmes.