Face PAD using Multi-Channel CNN

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.

Installation

The installation instructions are based on conda and works on Linux systems only. Install conda before continuing.

Once you have installed conda, download the source code of this paper and unpack it. Then, you can create a conda environment with the following command:

$ cd bob.paper.mccnn.tifs2018
$ conda env create -f environment.yml
$ source activate bob.paper.mccnn.tifs2018  # activate the environment
$ buildout
$ bin/bob_dbmanage.py all download --missing
$ bin/train_mccnn.py --help  # test the installation

This will install all the required software to reproduce this paper.

Configuring the experiments

Once the environment is ready. The WMCA database needs to be downloaded. For downloading the WMCA database, please check the following link Download Instructions.

After downloading the database, you need to set the paths to those in the configuration files. Bob supports a configuration file (~/.bob_bio_databases.txt) in your home directory to specify where the databases are located. The absolute path to the database and the location store the annotations should be specified. Please specify the paths for the database like below:

$ cat ~/.bob_bio_databases.txt
[YOUR_WMCA_DB_DIRECTORY] = /databases/WMCA/
[YOUR_WMCA_ANNOTATIONS_DIRECTORY] = /databases/WMCA/ANNOTATIONS/

Contact

For questions or reporting issues to this software package, contact our development mailing list.