This is a pre-production deployment of Warehouse, however changes made here WILL affect the production instance of PyPI.
Latest Version Dependencies status unknown Test status unknown Test coverage unknown
Project Description

This package provides the source code to run the experiments published in the paper An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms. It relies on the FaceRecLib to execute all face recognition experiments. Most of the face recognition algorithms are implemented in Bob, while one of them is taken from the CSU Face Recognition Resources.


Currently, this package only works in Unix-like environments and under MacOS. Due to limitations of the Bob library, MS Windows operating systems are not supported. We are working on a port of Bob for MS Windows, but it might take a while.


The experiments described in this section use the FaceRecLib in version 1.1.3, Bob in version 1.2.0 and the January 2012 release of the CSU Face Recognition Resources. These versions are pin-pointed in the file (see the install_requires section). For other versions, the results might be slightly different.


The installation of this package relies on the BuildOut system. By default, the command line sequence:

$ python
$ bin/buildout

should download and install most requirements, including the FaceRecLib, the Database interface packages for the BANCA database and the Good, the Bad & the Ugly database, and, finally, the Wrapper classes for the CSU Face Recognition Resources. Unfortunately, some packages must be installed manually:


To install the Bob toolkit, please visit and follow the installation instructions. Please verify that you have at least version 1.2.0 of Bob installed. If you have installed Bob in a non-standard directory, please open the buildout.cfg file from the base directory and set the ‘prefixes’ directory accordingly.

CSU Face Recognition Resources

Due to the fact that the CSU toolkit needs to be patched to work with the FaceRecLib, the setup is unfortunately slightly more complicated. To be able to run the experiments based on the CSU toolkit, i.e., the LDA-IR algorithm, please download the CSU Face Recognition Resources from After unpacking the CSU toolkit, it needs to be patched. For this reason, please follow the instructions:

  1. Patch the CSU toolkit:

    $ bin/buildout -c buildout-before-patch.cfg
  2. Update the buildout.cfg file by modifying the sources-dir = [YOUR_CSU_SOURCE_DIRECTORY] entry to point to the base directory of the patched version of the CSU toolkit.

Make sure that you update your installation by again calling:

$ bin/buildout


The patch file is only valid for the current version of the CSU toolkit (last checked in December 2012). If you have another version, please see the Getting help section.


At Idiap, you can also use the pre-patched version of the CSU toolkit. Just use:

$ bin/buildout -c buildout-idiap.cfg

instead of downloading and patching the CSU toolkit.


Of course, we are not allowed to re-distribute the original images to run the experiments on. To re-run the experiments, please make sure to have your own copy of the BANCA and the Good, the Bad & the Ugly images.


After installing you might want to create the documentation for this satellite package, which includes more detailed information on how to re-run the experiments and regenerate the scientific plots from the paper. To generate and open the documentation execute:

$ bin/sphinx-build docs sphinx
$ firefox sphinx/index.html

Of course, you can use any web browser of your choice.

Getting help

In case anything goes wrong, please feel free to open a new ticket in our GitHub page, or send an email to

Cite our paper

If you use the FaceRecLib or this package in any of your experiments, please cite the following paper:

       author = {G{\"u}nther, Manuel AND Wallace, Roy AND Marcel, S{\'e}bastien},
       editor = {Fusiello, Andrea AND Murino, Vittorio AND Cucchiara, Rita},
     keywords = {Biometrics, Face Recognition, Open Source, Reproducible Research},
        month = oct,
        title = {An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms},
    booktitle = {Computer Vision - ECCV 2012. Workshops and Demonstrations},
       series = {Lecture Notes in Computer Science},
       volume = {7585},
         year = {2012},
        pages = {547-556},
    publisher = {Springer Berlin},
     location = {Heidelberg},
          url = {}
Release History

Release History


This version

History Node

TODO: Figure out how to actually get changelog content.

Changelog content for this version goes here.

Donec et mollis dolor. Praesent et diam eget libero egestas mattis sit amet vitae augue. Nam tincidunt congue enim, ut porta lorem lacinia consectetur. Donec ut libero sed arcu vehicula ultricies a non tortor. Lorem ipsum dolor sit amet, consectetur adipiscing elit.

Show More

Download Files

Download Files

TODO: Brief introduction on what you do with files - including link to relevant help section.

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date (136.8 kB) Copy SHA256 Checksum SHA256 Source Sep 5, 2013

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS HPE HPE Development Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting