Resources for biometric experiments

bob.bio.base provides open-source tools to run comparable and reproducible biometric recognition experiments. It covers the following biometrics traits:

Get Started

This package defines the structure of biometric experiments. After installing the necessary environment, you can try out a simple comparison between two (or more) samples using a face recognition algorithm from bob.bio.face, for example. Run the following command:

$ bob bio compare-samples --pipeline facenet-sanderberg me.png not_me.png

The --pipeline option indicates which algorithm should be used to compare the pictures. The list of all available pipelines is available in the help text of the --pipeline option:

$ bob bio compare-samples --help
  ...
  Options:
    -p, --pipeline CUSTOM     Vanilla biometrics pipeline composed of a scikit-
                              learn Pipeline and a BioAlgorithm Can be a
                              ``bob.bio.pipeline`` entry point, a module name,
                              or a path to a Python file which contains a
                              variable named `pipeline`.Available entry points
                              are: ..., facenet-sanderberg, ...

Of course, with that command, you can run every possible biometric experiment by headbutting the problem and executing everything by hand. Or you could use the tools that we offer here to set up an experimentation pipeline, structure your data within a database interface and run a whole experiment in one swoop.

Citing our Publications

If you run biometric recognition experiments using the bob.bio framework, please cite at least one of the following in your scientific publication:

@inbook{guenther2016face,
  chapter = {Face Recognition in Challenging Environments: An Experimental and Reproducible Research Survey},
  author = {G\"unther, Manuel and El Shafey, Laurent and Marcel, S\'ebastien},
  editor = {Bourlai, Thirimachos},
  title = {Face Recognition Across the Imaging Spectrum},
  edition = {1},
  year = {2016},
  month = feb,
  publisher = {Springer}
}

@inproceedings{guenther2012facereclib,
  title = {An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms},
  author = {G\"unther, Manuel and Wallace, Roy and Marcel, S\'ebastien},
  editor = {Fusiello, Andrea and Murino, Vittorio and Cucchiara, Rita},
  booktitle = {European Conference on Computer Vision (ECCV) Workshops and Demonstrations},
  series = {Lecture Notes in Computer Science},
  volume = {7585},
  year = {2012},
  month = oct,
  pages = {547-556},
  publisher = {Springer},
}

Users Guide

Reference Manual

References

Auckenthaler2000

Auckenthaler, Roland, Michael Carey, and Harvey Lloyd-Thomas. “Score normalization for text-independent speaker verification systems.” Digital Signal Processing 10.1 (2000): 42-54.

Mariethoz2005

Mariethoz, Johnny, and Samy Bengio. “A unified framework for score normalization techniques applied to text-independent speaker verification.” IEEE signal processing letters 12.7 (2005): 532-535.

Mandasari2014

Mandasari, Miranti Indar, et al. “Score calibration in face recognition.” Iet Biometrics 3.4 (2014): 246-256.

Indices and tables