DFACE
Face redaction demo with the DFACE app. Detection made using 1.18sm model.

Face redaction demo with the DFACE app. Detection made using 1.18sm model.

DFACE.app #

DFACE.app is an automatic, private, open-source face redaction web app. It uses the YOLOV5 neural network object detection framework to run face detection in a web browser so photos never leave a user’s device. It can process up to 1,000 faces per image at down to 10x10 pixels per face with varying effects (color fill, blur, or emoji), and supports batch-processing multiple images. It is designed for activists and social media users to quickly and privately redact faces in imagery before posting to social media. The entire application uses only about 13MB of bandwidth and is open sourced with a MIT license at https://github.com/vframeio/dface.

Visit DFACE.app
DFACE.app screenshot.

DFACE.app screenshot.

DFACE was built with Jules LaPlace as part of the VFRAME project using YOLOV5, TF.js, and Next.js.

Research and development of DFACE (as part of the VFRAME project) received support through the NGI0 PET Fund, a fund established by NLnet with financial support from the European Commission’s Next Generation Internet programme, under the aegis of DG Communications Networks, Content and Technology under grant agreement No 825310.

To learn more about the VFRAME project visit VFRAME.io.