Skip to content

This project analyzes the impact of various face occlusions on the performance of SOTA face detection algorithms.

License

Notifications You must be signed in to change notification settings

mobilesec/occluded-facedetection-performance

Repository files navigation

Face detection performance on occluded faces

Installation

  • python3 -m venv env
  • source env/bin/activate
  • pip3 install -r requirements.txt
  • Download the CFP dataset
  • python -m ipykernel install --user --name=env
  • In a jupyter notebook with the env-kernel go through OccludedFaceDetection

License

Licensed under the EUPL.

Acknowledgement

This work has been carried out within the scope of Digidow, the Christian Doppler Laboratory for Private Digital Authentication in the Physical World, funded by the Christian Doppler Forschungsgesellschaft, 3 Banken IT GmbH, Kepler Universitätsklinikum GmbH, NXP Semiconductors Austria GmbH, and Österreichische Staatsdruckerei GmbH and has partially been supported by the LIT Secure and Correct Systems Lab funded by the State of Upper Austria.

About

This project analyzes the impact of various face occlusions on the performance of SOTA face detection algorithms.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published