Current Occupation
Currently, I am working as a research associate at the Vision and Security Technology (VaST) lab in the University of Colorado Colorado Springs (UCCS) under the supervision of
Prof. Terrance E. Boult.
Here, I am part of the
IARPA JANUS team investigating algorithms for unconstrained face recognition, including recognizing frontal and profile faces in unconstrained images and videos.
The basic idea of my current research is to automatically estimate facial attributes (such as: big nose, bushy eye-brows, gender, ...) from facial images, and use these attributes as kind of a soft biometric to identify the person in the image.
As almost every researcher does nowadays, I am working with deep convolutional neural networks, and I have implemented several extensions to the
Caffe framework, for example, a data layer to perform random rotation, scaling, shifting and blurring of training images in order to improve the stability of the network with respect to these transformations, which has been demonstrated in the AFAFCT paper at IJCB 2017, see below.
Another such layer is a balancing layer, which balanced biased data distributions in multi-objective optimization problems, which we have published in the MOON paper at ECCV 2015, see below.
Of course, I am also actively participating in many other topics of the VaST lab, which are: adversarial images, improved network training, adversarial stability, face clustering, open-set malware detection, and alike.
For example, together with some colleagues, we were running the
Unconstrained Face Detection and Open-Set Face Recognition Challenge, the results of which we present at IJCB 2017.
Finally, I am still a developer of
Bob (see below), though my activities there are a little limited lately.
Anyways, I found the time to present the biometrics framework in a hands-on tutorial on 2D face recognition, held in the
Biometrics Summer School 2016 in Kuala Lumpur, Malaysia.
Similarly, I present
Bob's Biometric Recognition Framework - A Hands-on Tutorial with Face Recognition Examples at
IJCB 2017 in Denver, Colorado.
Short Biography
In my early teenager times, I attended a high-school specialized for mathematics and natural science.
As the logical consequence, I studied computer science with mathematics as minor subject at the
Technical University of Ilmenau, Germany, starting in 1999.
In my diploma thesis that I wrote in 2004, I also had my first contact with the face recognition topic, which I am following for more than 10 years now.
I wrote my PhD thesis about face detection, recognition, classification, and visualization in the
Institute for Neural Computation at the
Ruhr-University in Bochum, Germany, under the supervision of
Dr. Rolf Würtz.
There, I developed a simple statistical model that needs only few training data and can be trained and applied fast.
Based on Gabor wavelet responses, I used my model to detect faces in images, recognized the person in the image, and classified, e.g., illumination conditions and facial expressions.
I had implemented my model into the
Pattern Recognition And Graph Matching Algorithms library, which unfortunately never was published as open source.
Furthermore, I established a system to classify genetic syndromes based on facial images and implemented a graphical user interface called FIDA (Facial Image Diagnostic Aid).
At the end of my time in
Bochum, I stepped on novel Gabor-wavelet-based features that turned out to be very successful for face recognition and facial landmark localization under uncontrolled illumination conditions.
My next career step was leading me to the
Idiap Research Institute, located in a small town
Martigny in the middle of the Alps in Switzerland, where I joined the Biometrics group under the supervision of
Dr. Sébastien Marcel.
There, I was part of the development team of
Bob, a free signal processing and machine learning toolbox for researchers, which is particularly designed to run biometric recognition experiments.
The interface of Bob is written in
Python, while the computationally intensive parts are implemented in C++ and bound to Python using the
Python C-API.
As the first step, I ported the Gabor wavelet based algorithms from my PhD thesis into Bob, resulting in the package bob.ip.gabor.
As another part of Bob, I developed the
bob.bio packages, an open source tool for the fair comparison of face recognition algorithms.
This tool allows to run face (and other biometric) recognition experiments choosing from a variety of preprocessing algorithms, different features to extract from the images, and a pool of face recognition algorithms, and you can run the algorithm on one of the many available image and video databases.
To assure comparability of the results, it is assured that default evaluation protocols are employed.
The bob.bio packages are designed in a way that makes it easy to implement your own preprocessor, feature, recognition algorithm or database, and you can simply plug in your code and combine it with the existing algorithms, and run an experiment to see whether your code works better than the existing one.
During my stay at Idiap, I became responsible for chairing the
competition on face recognition in mobile environment using the MOBIO database.
In this competition we found algorithms that can be used in real-world applications, i.e., when the image capture conditions cannot be controlled.
The baseline script, which can be taken as an example, can be downloaded
here.
If you want to see, how my Gabor features (see above) performed in the competition, you might want to download the
source code.
The competition was held synchronized with the
competition on speaker recognition.
At the end of this competition, we fused the results of the best face and the best speaker recognition algorithms to build an integrated verification system.
Details about the results of the competition and the fusion can be found in the ICB 2013 and BTFS 2013 papers listed below.
Professional Experience
The biggest field of research experience is on automatic face recognition.
During my PhD time I became an expert on Gabor wavelet based face detection and recognition.
I invented several methods to improve face detection, facial feature localization, and face recognition.
I also successfully used Gabor wavelet responses for classification, inventing a statistical model that was able to deal with small amounts of training data and that handled Gabor wavelet responses in a proper way.
At Idiap, I have worked with a broader spectrum of face recognition algorithms.
I have designed software and experiments to compare face recognition algorithms under different aspects such as facial expression, illumination, partial occlusion and non-frontal pose.
As I was giving a students programming exercise on Artificial Neural Networks, I am also familiar with that topic.
But I am not convinced that Neural Networks (as they are currently used) are the best choice to solve problems.
Up till now, I was implementing all my experiments in C++ and Python, and I have some experience with Java programming, the Java Native Interface (JNI), the Python C-API, and also with using
CMake, distributing mixed and inter-dependent C++/Python packages on the
Python Package Index (PyPI), writing publications in LaTeX, and writing my personal web page in HTML.
Of course, I also can work with Matlab and C, but I'd prefer to avoid these two languages as far as possible.
Teaching Experience
Lectures
Currently, I am teaching the
Data Structures and Algorithms course at UCCS.
This course is a beginners course in Java programming, which introduces the concepts of arrays, linked lists and binary trees, as well as searching and sorting algorithms based on these data structures.
During my PhD, I was leading the programming exercise of the
Artificial Neural Networks course at the
Institut für Neuroinformatik (Institute for Neural Computation) in Bochum, Germany.
There, students learned how to implement neural networks from scratch, including gradient descent to train these networks.
Also, radial basis function (RBF) networks, Kohonen maps and the growing neural gas algorithm was presented.
Student Supervision
PhD Students
- Andras Rozsa, Thesis: Towards Robust Deep Neural Networks, Vision and Security Technology Lab, University of Colorado Colorado Springs, 2018.
- Svati Bendale, Thesis: Learning based Visual Engagement, Visual Arousal and Self-Efficacy, Vision and Security Technology Lab, University of Colorado Colorado Springs, ongoing.
- Faris Kateb, Thesis: Perturbation and Adversarial Invariant Representation (PAIR), Vision and Security Technology Lab, University of Colorado Colorado Springs, 2018.
- James Henrydoss, Thesis: Incremental Open Set Intrusion Recognition, Vision and Security Technology Lab, University of Colorado Colorado Springs, ongoing.
- Ethan M. Rudd, Thesis: Better Learning through Improved Distributional Modelling, Vision and Security Technology Lab, University of Colorado Colorado Springs, 2017.
- Tiago de Freitas Pereira, direct supervision until 2015, Idiap Research Institute.
- Laurent El Shafey, Thesis: Scalable Probabilistic Models for Face and Speaker Recognition, Idiap Research Institute, 2014.
Master Students
- Akshay Raj Dhamija, Thesis: OpenSet approach towards Object Detection, Vision and Security Technology Lab, University of Colorado Colorado Springs, 2017.
- Micheal Bihn, Thesis: Evaluating Short-Wave Infrared images on VGGFace, Vision and Security Technology Lab, University of Colorado Colorado Springs, 2017.
- Dennis Haufe, Thesis: Gabor phases for face classification, Institut für Neuroinformatik, Ruhr-Universität Bochum, 2011.
Bachelor Students
- Benedikt Stratmann, Thesis: Einfluss der Graphenstruktur auf die Leistung eines Gesichtserkennungssystems, Institut für Neuroinformatik, Ruhr-Universität Bochum, 2010.
- Arzu Sarial, Thesis: Mimikerkennung durch Graphenvergleich, Institut für Neuroinformatik, Ruhr-Universität Bochum, 2009.
- Norbert Neuser, Thesis: Die Auswirkungen von Positionierungsfehlern auf graphenbasierte Gesichtserkennung, Institut für Neuroinformatik, Ruhr-Universität Bochum, 2008.
- Dennis Haufe, Thesis: Einfluss der Bildauflösung auf Gesichtserkennung durch Graphenvergleich, Institut für Neuroinformatik, Ruhr-Universität Bochum, 2008.
Publications
2018
-
Chunchun Li, Manuel Günther, and Terrance E. Boult.
ECLIPSE: Ensembles of Centroids Leveraging Iteratively Processed Spatial Eclipse Clustering.
International Conference on Winter Applications in Computer Vision (WACV), 2018.
-
Andras Rozsa, Manuel Günther, and Terrance E. Boult.
Towards Robust Deep Neural Networks With BANG.
International Conference on Winter Applications in Computer Vision (WACV), 2018.
arXiv ID 1612.00138
-
Michael Bihn, Manuel Günther, Daniel Lemmond, and Terrance E. Boult.
Evaluating a Convolutional Neural Network on ShortWave Infra-Red Images.
International Conference on Winter Applications in Computer Vision (WACV) Cross-Domain Face Recognition Workshop, 2018.
-
Ethan M. Rudd, Manuel Günther, Akshay Raj Dhamija, Faris A. Kateb, and Terrance E. Boult.
What's Hiding in My Deep Features?
Deep Learning in Biometrics, CRC Press, 2018
2017
-
Manuel Günther, Andras Rozsa, and Terrance E. Boult.
AFFACT: Alignment-Free Facial Attribute Classification Technique.
International Joint Conference on Biometrics (IJCB), 2017.
arXiv ID 1611.06158;
Trained Caffe networks
-
Manuel Günther, and others.
Unconstrained Face Detection and Open-Set Face Recognition Challenge.
International Joint Conference on Biometrics (IJCB), 2017.
arXiv ID 1708.02337;
competition website
-
Andras Rozsa, Manuel Günther, and Terrance E. Boult.
LOTS about Attacking Deep Features.
International Joint Conference on Biometrics (IJCB), 2017.
arXiv ID 1611.06179
-
André Anjos, Manuel Günther, Tiago de Freitas Pereira, Pavel Korshunov, Amir Mohammadi, Sébastien Marcel.
Continuously Reproducing Toolchains in Pattern Recognition and Machine Learning Experiments.
International Conference on Machine Learning (ICML) Workshop on Reproducibility in Machine Learning, 2017.
pdf;
source code
-
Andras Rozsa, Manuel Günther, and Terrance E. Boult.
Adversarial Robustness: Softmax versus Openmax.
British Machine Vision Conference (BMVC), 2017. (to appear)
arXiv ID 1708.01697
-
Manuel Günther, Steve Cruz, Ethan M. Rudd, and Terrance E. Boult.
Toward Open-Set Face Recognition.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017.
arXiv ID 1705.01567
-
James Henrydoss, Steve Cruz, Ethan M. Rudd, Manuel Günther, and Terrance E. Boult.
Incremental Open Set Intrusion Recognition Using Extreme Value Machine.
IEEE International Conference on Machine Learning and Applications (ICMLA), 2017.
Won Best Poster award.
-
Ethan M. Rudd, Andras Rozsa, Manuel Günther, and Terrance E. Boult.
A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions.
IEEE Communications Surveys & Tutorials, 2017.
arXiv ID 1603.06028
2016
-
Andras Rozsa, Manuel Günther, and Terrance E. Boult.
Are Accuracy and Robustness Correlated?
15th IEEE International Conference on Machine Learning and Applications (ICMLA), 2016.
arXiv ID 1610.04563
-
Andras Rozsa, Manuel Günther, Ethan M. Rudd, Terrance E. Boult.
Are Facial Attributes Adversarially Robust?
23rd International Conference on Pattern Recognition (ICPR), 2016.
arXiv ID 1605.05411
Won Best Student Paper award.
-
Ethan M. Rudd, Manuel Günther, Terrance E. Boult.
MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes.
The 14th European Conference on Computer Vision (ECCV), 2016.
arXiv ID 1603.07027;
Trained Caffe networks
-
Ethan M. Rudd, Manuel Günther, Terrance E. Boult.
PARAPH: Presentation Attack Rejection by Analyzing Polarization Hypotheses.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016.
arXiv ID 1605.03124
-
Manuel Günther, Laurent El Shafey, Sébastien Marcel.
Face Recognition in Challenging Environments: An Experimental and Reproducible Research Survey.
Face Recognition Across the Imaging Spectrum, Springer, 2016.
pdf;
source code
2015
-
Abhishek Dutta, Manuel Günther, Laurent El Shafey, Sébastien Marcel, Raymond Veldhuis and Luuk Spreeuwers.
Impact of Eye Detection Error on Face Recognition Performance.
IET Biometrics, 2015.
pdf;
source code
-
Manuel Günther, Stefan Böhringer, Dagmar Wieczorek and Rolf P. Würtz
Reconstruction of Images from Gabor Graphs with Applications in Facial Image Processing.
Journal of Wavelets, Multiresolution and Information Processing, 2015.
pdf
- Rakesh Metha, Manuel Günther and Sübastien Marcel.
Gender Classification by LUT based boosting of Overlapping Block Patterns.
Scandinavian Conference on Image Analysis (SCIA), 2015.
pdf;
source code
2014
-
Miranti I. Mandasari, Manuel Günther, Roy Wallace, Rahim Saedi, Sébastien Marcel and David Van Leeuwen.
Score Calibration in Face Recognition.
IET Biometrics, 2014.
pdf;
source code
-
Elie Khoury, Laurent El Shafey, Chris McCool, Manuel Günther and Sébastien Marcel.
Bi-modal Biometric Authentication on Mobile Phones in Challenging Conditions.
Image and Vision Computing (IVC), 2014.
pdf
2013
-
Elie Khoury, Manuel Günther, Laurent El Shafey and Sébastien Marcel.
On the Improvements of Uni-modal and Bi-modal Fusions of Speaker and Face Recognition for Mobile Biometrics.
Biometric Technologies in Forensic Science (BTFS), 2013.
pdf;
source code
-
Manuel Günther, and others.
The 2013 Face Recognition Evaluation in Mobile Environment.
The 6th IAPR International Conference on Biometrics (ICB), 2013.
pdf
-
Elie Khoury, and others.
The 2013 Speaker Recognition Evaluation in Mobile Environment.
The 6th IAPR International Conference on Biometrics (ICB), 2013.
pdf
2012
-
Manuel Günther, Roy Wallace and Sébastien Marcel.
An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms.
European Conference on Computer Vision (ECCV), Workshops and Demonstrations: 547-556, 2012.
pdf;
source code
-
André Anjos, Laurent El Shafey, Roy Wallace, Manuel Günther, Chris McCool and Sébastien Marcel.
Bob: a Free Signal Processing and Machine Learning Toolbox for Researchers.
Proceedings of the ACM Multimedia Conference, 2012.
pdf;
home page
-
Manuel Günther, Dennis Haufe, Rolf P. Würtz.
Face Recognition with Disparity Corrected Gabor Phase Differences.
Artificial Neural Networks and Machine Learning (ICANN): 411-418, 2012.
pdf
2011
-
Manuel Günther.
Statistical Gabor Graph Based Techniques for the Detection, Recognition, Classification, and Visualization of Human Faces.
PhD thesis, Institut für Neuroinformatik, Technische Universität Ilmenau, 2011.
pdf
-
Harald J. Schneider, Robert P. Kosilek, Manuel Günther, J. Römmler., G.K. Stalla, C. Sievers, M. Reincke, Jochen Schopohl and Rolf P. Würtz.
A novel approach to the detection of acromegaly: accuracy of diagnosis by automatic face classification.
Journal of Clinical Endocrinology and Metabolism, 2011.
- Stefan Böhringer and others.
Genetic determination of human facial morphology: links between cleft-lips and normal variation.
European Journal of Human Genetics, 2011.
-
Stefan Böhringer, Manuel Günther, Stella Sinigerova, Rolf P. Würtz, Berard Horsthemke and Dagmar Wieczorek.
Automated Syndrome Detection in a set of Clinical Facial Photographs.
American Journal of Medical Genetics, 2011.
Earlier
-
Manuel Günther, Marco K. Müller and Rolf P. Würtz.
Two kinds of Statistics for Better Face Recognition.
International Conference on Numerical Analysis and Applied Mathematics (ICNAAM): 1901-1904, 2010.
pdf
-
Manuel Günther and Rolf P. Würtz.
Face detection and recognition using maximum likelihood classifiers on Gabor graphs.
International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), 23(3):433-461, 2009.
pdf
-
Manuel Günther.
Klassifikation von Gesichtern mit optimierten lokalen Graphen auf 2D und 3D Bilddaten.
Diploma thesis, Technische Universität Ilmenau, 2005.