Face PAD using Multi-Channel CNNs

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

@inproceedings{GeorgeTIFS2019,
    author = {Anjith George, Zohreh Mostaani, David Geissenbuhler, Olegs Nikisins, Andre Anjos, Sebastien Marcel},
    title = {Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network},
    year = {2019},
    booktitle = {TIFS 2019},
}

If you use this package and/or its results, please cite the paper [GMGNAM19].

User guide

• Running baselines in grandtest protocol of WMCA
  • A. Color channel
  • B. Depth channel
  • C. Infrared channel
  • D. Thermal channel
  • E. Score fusion (Haralick-SVM)
  • F. Score fusion (IQM-LBP-LR)
• BASELINES in LOO protocols (for score fusion)
  • A. Color
  • B. Depth
  • C. Infrared
  • D. Thermal
  • E. Score fusion
• BASELINES in LOO protocols (Haralick-SVM)
  • Color
  • Score fusion Haralick-SVM
  • Scoring for Haralick Mean fusion
• Training FASNet for face PAD
  • Preprocessing
  • Training FASNET
  • Running experiments with the trained model
  • Evaluating results
• Training MCCNN for face PAD
  • Preprocessing data
  • Training MCCNN
  • Running experiments with the trained model
  • Evaluating results
• Using pretrained models
• References