Learning One Class Representations for PAD

This package is part of the Bob toolkit and it allows to reproduce the experimental results published in the following paper:

@inproceedings{GeorgeTIFS2020,
    author = {Anjith George, Sebastien Marcel},
    title = {Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networks},
    year = {2020},
    booktitle = {TIFS 2020},
}

If you use this package and/or its results, please cite the paper [GM20].

User guide

• Running baselines in grandtest protocol of WMCA
• BASELINES in Other protocols
• Training MCCNN-OCCL-GMM for face PAD
  • Preprocessing data
  • Training MCCNN-OCCL-GMM
  • Running experiments with the trained model
  • Evaluating results
• Using pretrained models
• References