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.
Credits:
VFRAME development is currently supported by a grant from the German Federal Ministry of Education and Research (BMBF).
Websites:
