Open Source Face Recognition Library

This package provide open source tools to run comparable and reproducible face recognition experiments. This includes:

• Preprocessors to detect, align and photometrically enhance face images

• Feature extractors that extract features from facial images

• Facial image databases including their protocols.

• Scripts that trains CNNs for face recognition.

Get Started

First, complete Bob’s installation instructions. Then, to install this package, do this:

$ conda activate <myenv>
(<myenv>) $ conda install bob.bio.face

The simplest experiment

The easiest way to get started is by simply comparing two faces:

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

Warning

No face detection is carried out with this command.

Check out all the face recognition algorithms available by doing:

$ resources.py --types p

Get Started, serious

For detailed information on how this package is structured and how to run experiments with it, please refer to the documentation of bob.bio.base and get to know the PipelineSimple and how to integrate both, algorithm and database protocols with it.

Users Guide

• Executing Baseline Algorithms
  • Baselines available
• Setting up Facial Image Databases
• Leaderboard
  • Datasets
• References
• Face Annotators
• FAQ
  • How to crop a face ?
  • How to choose the cropped positions ?

Reference Manual

• Tools implemented in bob.bio.face
  • Summary
  • Databases
  • Annotators
  • Preprocessors
  • Utilities

Todo

Add reference results.

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/arface.rst, line 74.)

Todo

Add reference results.

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/gbu.rst, line 73.)

Todo

To be done

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/meds.rst, line 10.)

Todo

To be done

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/morph.rst, line 10.)

Todo

Benchmarks on Multipie Database

Probably for Manuel’s students

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/multipie.rst, line 9.)

Todo

Add reference results.

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/scface.rst, line 78.)

Todo

To be done

(The original entry is located in /scratch/builds/bob/bob.bio.face/doc/leaderboard/uccs.rst, line 10.)