VFRAME is a computer vision toolkit designed for human rights researchers and investigative journalists. It provides customized state-of-the-art tools for object detection and quantification, scene classification, visual search, image annotation for creating datasets, APIs to integrate with existing workflows, the ability to train new algorithms, and graphic content filtering algorithms to reduce exposure to traumatic content. VFRAME is currently working directly with the Syrian Archive project to establish the most effective and relevant technologies to accelerate their work on documenting the Syrian conflict. The VFRAME computer vision toolkit along with the methodologies and API examples will all be published as open source material as the project develops further.
The main goals of this project are to provide innovative tools designed specifically for human rights researchers and to publish clear documentation and web-based demos that facilitate engagement with these issues from a wider and non-technical audience. Anyone with access to the project website will eventually be able to test the computer vision algorithms and explore the datasets created for VFRAME project collaborations.
VFRAME development is currently supported by a grant from the German Federal Ministry of Education and Research (BMBF).
Adam Harvey (US) is an artist and researcher based in Berlin whose work explores the topics of privacy, surveillance, and biometrics. Harvey is a graduate of the Interactive Telecommunications Program at New York University (2010) and the founder of the Privacy Gift Shop (2013). His previous projects include developing a proof-of-concept camouflage against face detection (CV Dazzle, 2010), thermally reflective clothing to evade military drones (Stealth Wear, 2013), and a low-cost WiFi geolocation spoofing device (SkyLift, 2015). His work has been featured widely in publications and is included in the permanent collection at the Victoria and Albert Museum in London.