Skip to main content

Antispoofing cross database testing

Project description

This package contains scripts that permit to make a cross database testing in face antispoofing countermeasures in order evaluate them generalization power.

If you use this package and/or its results, please cite the following publications:

  1. The original paper with the fusion of countermesures explained in details:

      author = {de Freitas Pereira, Tiago and Anjos, Andr{\'{e}} and De Martino, Jos{\'{e}} Mario and Marcel, S{\'{e}}bastien},
      month = Jun,
      title = {Can face anti-spoofing countermeasures work in a real world scenario?},
      journal = {International Conference on Biometrics 2013},
      year = {2013},
  2. Bob as the core framework used to run the experiments:

      author = {A. Anjos AND L. El Shafey AND R. Wallace AND M. G\"unther AND C. McCool AND S. Marcel},
      title = {Bob: a free signal processing and machine learning toolbox for researchers},
      year = {2012},
      month = oct,
      booktitle = {20th ACM Conference on Multimedia Systems (ACMMM), Nara, Japan},
      publisher = {ACM Press},


There are 2 options you can follow to get this package installed and operational on your computer: you can use automatic installers like pip (or easy_install) or manually download, unpack and use zc.buildout to create a virtual work environment just for this package.

Using an automatic installer

Using pip is the easiest (shell commands are marked with a $ signal):

$ pip install antispoofing.crossdatabase

You can also do the same with easy_install:

$ easy_install antispoofing.crossdatabase

This will download and install this package plus any other required dependencies. It will also verify if the version of Bob you have installed is compatible.

This scheme works well with virtual environments by virtualenv or if you have root access to your machine. Otherwise, we recommend you use the next option.

Using zc.buildout

Download the latest version of this package from PyPI and unpack it in your working area. The installation of the toolkit itself uses buildout. You don’t need to understand its inner workings to use this package. Here is a recipe to get you started:

$ python
$ ./bin/buildout

These 2 commands should download and install all non-installed dependencies and get you a fully operational test and development environment.

User Guide

First of all, it is necessary to be familiarized with the satellite packages: antispoofing.motion and antispoofing.lbptop. The antispoofing.lbptop satellite package generates the scores of the LBP-TOP and LBP countermeasures.

Crossdatabase test

The examples bellow show how to reproduce the performance using the inter-database protocol.

For each countermeasure trained and tuned with the Replay Attack Database, to get the performance using the test set of the Casia FASD, just type:

$ ./bin/ --scores-dir <scores_replay_countermeasure_directory> -d replay -t casias_fasd:

For each countermeasure trained and tuned with the Casia FASD, to get the performance using the test set of the Replay Attack Database, just type:

$ ./bin/ --scores-dir <scores_casia_countermeasure_directory> -d casia_fasd -t replay

Training all data

To get the performance using a countermeasure trained and tuned with both databases (Replay Attack Database and Casia FASD) just type:

To report the results using the Replay Attack Database:

$ ./bin/ --scores-dir <scores_all_countermeasures_directory> -d all -t replay

To report the results using the Casia FASD:

$ ./bin/ --scores-dir <scores_all_countermeasures_directory> -d all -t casia_fasd


For each countermeasures, to get the performance using the Score Level Fusion based Framework just type:

To report the results using the Replay Attack Database:

$ ./bin/ --scores-dir <scores_trained_with_replay> <scores_trained_with_casia> -d all -t replay --normalizer MinMaxNorm --fusion-algorithm SUM

To report the results using the Casia FASD:

$ ./bin/ --scores-dir <scores_trained_with_casia> <scores_trained_with_replay> -d all -t casia_fasd --normalizer MinMaxNorm --fusion-algorithm SUM


In case of problems, please contact any of the authors of the paper.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution (27.8 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page