Skip to main content

Running the face recognition experiments as given in paper: "An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms".

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.

Installation

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

$ python bootstrap.py
$ 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:

Bob

To install the Bob toolkit, please visit http://www.idiap.ch/software/bob/ 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 http://www.cs.colostate.edu/facerec. 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
    $ bin/patch_CSU.py [YOUR_CSU_SOURCE_DIRECTORY]
  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

Databases

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.

Documentation

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 manuel.guenther@idiap.ch.

Cite our paper

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

@inproceedings{Guenther_BeFIT2012,
       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 = {http://publications.idiap.ch/downloads/papers/2012/Gunther_BEFIT2012_2012.pdf}
}

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

xfacereclib.paper.BeFIT2012-1.0.0.zip (136.8 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