xfacereclib.extension.CSU 2.0.0

Wrapper classes to use the PythonFaceEvaluation classes from the CSU Face Recognition Resources

FaceRecLib Wrapper classes for the CSU Face Recognition Resources

This satellite package to the FaceRecLib provides wrapper classes for the CSU face recognition resources, which can be downloaded from http://www.cs.colostate.edu/facerec. Two algorithms are provided by the CSU toolkit (and also by this satellite package): the local region PCA (LRPCA) and the LDA-IR (also known as CohortLDA).

For more information about the LRPCA and the LDA-IR algorithm, please refer to the documentation on http://www.cs.colostate.edu/facerec/. For further information about the FaceRecLib, please read its Documentation. On how to use this package in a face recognition experiment, please see http://pypi.python.org/pypi/xfacereclib.paper.BeFIT2012

Installation Instructions

The current package is just a set of wrapper classes for the CSU facerec2010 module, which is contained in the CSU Face Recognition Resources, where you need to download the Baseline 2011 Algorithms. Please make sure that you have read installation instructions in the Documentation of this package on how to patch the original source code to work with our algorithms, before you try to go on woth this package.

Note

Since the original CSU resources are not Python3 compatible, this package only supports Python2. For external dependencies of the CSU resources, please read their README.

The FaceRecLib and parts of this package rely on Bob, an open-source signal-processing and machine learning toolbox. For Bob to be able to work properly, some dependent packages are required to be installed. Please make sure that you have read the Dependencies for your operating system.

Documentation

For further documentation on this package, please read the Stable Version or the Latest Version of the documentation.

For a list of tutorials on packages ob Bob, or information on submitting issues, asking questions and starting discussions, please visit its website.