PhD Toolbox

The PhD (Pretty helpful Development functions for) face recognition toolbox is a collection of Matlab functions and scripts intended to help researchers working in the field of face recognition. The toolbox was produced as a byproduct of the research work presented here and here and is freely available for download. It includes implementations of several state-of-the-art face recognition techniques as well as a number of demo scripts, which can be extremely useful for beginners in the field of face recognition.

The PhD toolbox features implementations of several early face recognition techniques, such as principal component analysis, linear discriminant analysis, kernel principal component analysis, or kernel fisher analysis. In addition to these techniques, it contains functions for Gabor filter construction, Gabor feature extraction, phase congruency computation and others. An important part of the toolbox are also the evaluation tools that allow for the construction of the most common performance curves (e.g., ROC, DET, CMC, EPC) used for evaluating face recognition systems.

In addition to the above, the toolbox also features a large number of demo scripts that demonstrate how to use the functions from the toolbox in face recognition experiments using a real database. These scripts demonstrate the complete procedure of building and testing face recognition systems based on Gabor filters and subspace projection techniques.


Browse through the PhD toolbox manual HERE.


Download the PhD toolbox from:


If you use the PhD toolbox for your research work, please cite the following publications:

title = {The Complete Gabor-Fisher Classifier for Robust Face Recognition},
author = {Vitomir Štruc and Nikola Pavešić},
doi = {10.1155/2010/847680},
year = {2010},
journal = {EURASIP Advances in Signal Processing},
volume = {2010},
pages = {26},
title = {Strengths and weaknesses of deep learning models for face recognition against image degradations},
author = {Klemen Grm and Vitomir Štruc and Anais Artiges and Matthieu Caron and Hazim K. Ekenel},
url = {},
year = {2017},
date = {2017-01-01},
journal = {IET Biometrics},
volume = {7},
number = {1},
pages = {81--89},
publisher = {IET},