VFRAME: Visual Forensics and Metadata Extraction
VFRAME is a computer vision toolkit designed for investigative purposes, aiming to bridge the gap between state-of-the-art artificial intelligence material used in the commercial sector and what is currently accessible to both human-rights researchers and investigative journalists. The software toolkit can process video collections by acting as a visual search engine. By locating similar images, the kit unlocks greater capacity for efficient data-analysis on a vast scale. Humanitarian researchers and activists rely on videos shared online to document war crimes and human rights violations. Manually reviewing this footage can be expensive, labour-intensive and often deeply traumatic.