Past Events

Since the end of 2019, the whole world has been living with the effects of the COVID-19 disease. Due to the airborne nature of the novel coronavirus, the COVID-19 disease has spread rapidly in many countries in a short time and has also been declared a global pandemic. Several preventive measures were implemented to reduce the spread of this disease, including social distancing, wearing face masks, avoiding large crowds, and others.

To help monitor public behavior and compliance with the implemented prevention measures, to gather reliable data for epidemiological models, facilitate authorized access and authentication, ensure safety and security despite the COVID-19 pandemic, it is critical to develop automated machine learning and computer vision based techniques that can help with these tasks. The COVID-19 pandemic has initiated research and development of computer-aided systems that can be used to prevent and monitor not only COVID-19 but also similar diseases that may appear in the future.

The goal of this workshop is to present the most recent and advanced work related to face and gesture analysis in the scope of COVID-19. We are interested in all COVID-19 related studies that focus on the detection of face mask, subjects' behaviors in public areas, analysis of pandemic and preventions-related real-world face and gesture data, prevention control and monitoring systems for unconstrained real-world conditions and related problems.

Presentation Attack Detection (PAD) ranks among the most controversial and challenging topics in the identity industry. Foundational to trust, a modern identity system must at a minimum detect fraudulent spoof attempts while enabling convenient, accurate identification and matching. Most biometric PAD systems are quite simple in concept but dramatically complex in execution. During this talk, Andrew explores the journey Integrated Biometrics took from early trials and errors to the modern successful ecosystem of technology they deploy. By examining this specific case study within fingerprint biometrics, the audience will take away general principles broadly applicable to the identity industry.

Curriculum vitæ

Andrew Wise is the Director of Quality at Integrated Biometrics. His technical leadership helps drive improvement of core system architectures, control processes, and automated validation testing. He has written numerous white papers on PAD and was a leading member of the team that developed and deployed IB’s current PAD ecosystem. In previous roles at IB, he worked on design teams to optimize electronics hardware while incorporating FMEA principles. He received a Bachelor of Science in Electrical Engineering and a Minor in Leadership in 2018 from Virginia Polytechnic Institute and State University.

Workshop of the Biometrics Working Group of TeleTrusT, the IT Security Association in Germany

Come, celebrate our 10^th anniversary with us :)

This workshop will present an update on the latest development on Face Image Quality.

This update will address through talks and panel discussions the following topics:

• current state of the art of face image quality metrics
• experience from stakeholder and requirements
• introduction of training concepts
• testing program (FRVT)
• standardization process

The NIST and the ISO/IEC SC37 WG3 are dedicated to promote ISO/IEC 29794-5.

Co-sponsors of this event:

NIST

ISO/IEC JTC1 SC37

SILVER Sponsor of this event:

Sponsors of this event:

Application of convolutional deep networks into face recognition systems reduces some of the problems with face alignment in images that have significant impact on the results in the previously used methods. However large variation in head pose still might be the issue even for modern algorithms. It is natural to think of applying 3D image processing methods to solve the problem of algorithms reliability over pose changes. Solutions based on native 3D data like point clouds and voxel grids can be infeasible because of heavy structures and more difficult to collect databases. One of the recently proposed approaches is to decompose the object into the set of multiview 2D images. For faces, collecting the sets of different view images is also typical for police booking photography. In this talk she will analyze some of the multiview recognition methods, like MVCNN and RotationNet, in application to face identification databases.

Curriculum vitæ

Weronika Gutfeter is a research assistant in Biometric and Machine Intelligence Laboratory of Research and Academic Computer Network (NASK) in Warsaw, Poland. She obtained her Master’s degree in Computer Engineering at Warsaw University of Technology and now she works on her PhD thesis that covers a topic of 3D, semi-3D and multiview face identification. Her research interests include also other computer vision methods like algorithms for human detection in depth and thermal images. In NASK she works on developing machine learning systems for government and public sector.

The German biometrics standardisation group (DIN) and EAB are proud to present the Workshop on the Artificial Intelligence Act (AIA) on November 10. This workshop regarding the AIA and international standardization of AI gathers the biometrics and AI standardisation community in order to learn and discuss possible implications, through talks and break out sessions.

We thank our media partner:

Biometric identification is the most prominent and most complex application domain within the scope of the proposed EU AI regulation. The regulation will prohibit certain use cases of AI-/ML-based biometric identification system, and classify others as high-risk. In this seminar Prof. Dr. Oliver Haase will give an overview of the regulation's classification rules, the requirements on high-risks systems, and the procedure for conformity assessment.

Curriculum vitæ

Prof. Dr. Oliver Haase has a background in software engineering and software verification. In recent years he has focused on the regulatory requirements for AI-/ML-based, safety-critical systems. In this capacity, he has helped numerous medical device manufacturers to get their AI-based products into the market. He is a co-founder and managing director of Validate ML GmbH, a company that specialises on the validation of safety-critical ML systems.

The Norwegian Biometrics Forum (NBF) is an open platform dedicated to regular exchange of information and experience related to the field of Biometrics. The target of the group is the interdisciplinary discussion between research, technology developers, data privacy experts, governmental agencies and operators of Biometric Systems. In the regular meetings new applications, latest research results and products are presented.

This Lunch Talk will be a conversation around the use of biometric data particularly in the migration management context. It will cover some of the potential impacts of this use on the fundamental rights of migrants, particularly the impacts on migrant children. The intention here is to focus slightly less on the purely technical side of biometrics, and to highlight some of the impacts associated with the use of this data in different contexts.

Curriculum vitæ

Bianca-Ioana Marcu's background is at the intersection of data protection, law, migration and fundamental rights. She is a certified Data Protection Officer and previously worked a lot with the GDPR in practice. She is currently undertaking PhD research at the Law, Science, Technology and Society (LSTS) research group at the Vrije Universiteit Brussel (VUB), and is the managing director of the annual computers, privacy and data protection conference in Brussels.

In the same way that face recognition algorithms suffer from bias due to the way they have been trained, anti-spoofing algorithms may undergo such limitations if the bias is not mitigated during the training phase. To make algorithms as robust as possible towards human diversity Unissey uses knowledge distillation. It is a technique enabling a student model to learn the generalization power of a cumbersome teacher. Here, Unissey presents a distillation process where multiple experts trained to be excellent on their respective domain teach a student model to mimic their individual performances and eventually become excellent on every domain. Unissey shows how this technique can be used to mitigate bias related to gender and ethnicity.

Curriculum vitæ

Idriss Mghabbaris currently a computer vision engineer at Unissey where he is working on presentation attack detection. Previously Idriss interned at BNP Paribas, the largest French banking group, where he worked on machine translation using neural networks. Idriss graduated from Centrale Paris and Ecole Normale Supérieure of Cachan.

The topic of human facial analysis has engaged researchers in multiple fields including computer vision, biometrics, forensics, cognitive psychology and medicine. Interest in this topic has been fueled by scientific advances that suggest insight into a person’s identity, intent, attitude, as well as health; all solely based on their face images and videos. The above leads to the tantalizing question: “What’s in a Face?”

In this talk Antitza will present recent works on face analysis, where the team has designed deep convolutional neural networks (CNNs) targeted to (a) cross spectral face recognition, as well as (b) analyse the complex state of apathy from face videos. While a large body of work was aimed at extracting and classifying such information from faces, currently the inverse problem — namely face generation — has received increased attention. In this context, she will talk about recent designed generative models, which allow for realistic generation of face videos, and the related deepfake detection.

Curriculum vitæ

Antitza Dantcheva is a Research Scientist with the STARS team of INRIA Sophia Antipolis, France. Previously, she was a Marie Curie fellow at INRIA and a Postdoctoral Fellow at the Michigan State University and the West Virginia University, USA. She received her Ph.D. degree from Télécom ParisTech/Eurecom in image processing and biometrics in 2011. Her research is in computer vision and specifically in designing algorithms that seek to learn suitable representations of the human face in interpretation and generation. She is recipient among others of the Best Poster Award at IEEE FG 2019, winner of the Bias Estimation in Face Analytics (BEFA) Challenge at ECCV 2018 (in the team with Abhijit Das and Francois Bremond) and Best Paper Award (Runner up) at the IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2017).

Biometrics provides efficient and reliable solutions to recognize individuals. With increasing number of identity theft and miss-use incidents we do observe a significant fraud in e-commerce and thus growing interests on trustworthiness of person authentication. Nowadays we find biometric applications in areas like border control, national ID cards, e-banking, e-commerce, e-health etc. Large-scale applications such as the upcoming European Union Entry Exit System (EES), the Visa Information System (VIS) and Unique Identification (UID) in India require high accuracy and also reliability, interoperability, scalability and usability. Many of these are joint requirements also for forensic applications.

Multimodal biometrics combined with fusion techniques can improve recognition performance. Efficient searching or indexing methods can accelerate identification efficiency. Additionally, quality of captured biometric samples can strongly influence the performance. Moreover, mobile biometrics is an emerging area and biometrics-based smartphones can support deployment and acceptance of biometric systems.

However, concerns about security and privacy cannot be neglected. The relevant techniques in the area of presentation attack detection (liveness detection) and template protection are about to supplement biometric systems, in order to improve fake resistance, prevent potential attacks such as cross-comparison, identity theft etc.

The BIOSIG 2021 conference addresses these issues and will present innovations and best practices that can be transferred into future applications. The conference is jointly organized by the Competence Center for Applied Security Technology (CAST), the German Federal Office for Information Security (BSI), the European Association for Biometrics (EAB), the TeleTrusT-Association, the Norwegian Biometrics Laboratory (NBL), National Research Center for Applied Cybersecurity (ATHENE), the Fraunhofer Institute for Computer Graphics Research IGD, IET Biometrics Journal and the special interest group BIOSIG of the Gesellschaft für Informatik e.V. (GI). The conference will be technically co-sponsored by IEEE and papers will be added to IEEE Xplore.

This training aims to provide an opportunity to learn first-hand from world-leading experts both the basics of biometric systems and also the latest developments across the community. It is aimed at a wide range of stakeholders including industrial and governmental developers and end-users, researchers, academics and post-graduate students, and policy makers.

Sponsor of this event:

EAB is launching the fifteenth European Biometric Max Snijder, Research, and Industry Awards. These prestigious awards are granted annually to individuals who have been judged by a panel of internationally respected experts to be making a significant contribution to the field of biometrics research in Europe.

GOLD sponsors of this event:

All members of EAB are invited to join us for our annual General Assembly.

The 8^th edition of the EAB Research Projects Conference will take place as virtual conference from 13 to 15 September 2021. The conference is organized by the European Association on Biometrics (EAB) in cooperation with the Joint Research Center (DG JRC) of the European Commission, through its Cyber and Digital Citizens’ security Unit. The EAB-RPC 2021 will be co-located with the EAB Biometrics Research, Industry and Max-Snijder-Awards and the IEEE BIOSIG Conference, later that same week.

The conference is currently the largest event on research funded by the European Union in the area of Biometrics and Identity Management. Over the previous successful editions, EAB-RPC has become the main forum in Europe where attendees can simultaneously: promote research carried out in biometrics, forge new links and networks, and identify the appropriate partners for possible future project applications. Last year’s edition welcomed over 100 participants from academia, industry and public institutions.

DIAMOND sponsors of this event:

We thank our partners:

Workshop of the Biometrics Working Group of TeleTrusT, the IT Security Association in Germany

Our society functions based on trust, in both the physical and the digital worlds. Unfortunately, just like crimes in the real world, cybercrimes, particularly identity fraud/theft and synthetic identities, also thrive in the digital age, thus eroding the trust we have on digital identity-based systems. These systems can range from vaccination certificates and eCommerce to government digital portals. In this talk, Norman will explain why a digital identity is stronger when it is bound to biometrics; and define the different levels of binding strength. A good digital identity system must be usable, inclusive, secure and resilient against attacks such as biometric presentation attack and document presentation attack. To this end, Norman will explain the required technologies to secure a digital identity system, such as privacy-preserving biometrics, computer vision, deep learning and cryptography.

Curriculum vitæ

Dr Norman Poh is the Chief Science Officer of Trust Stamp. He currently provides technical leadership to accelerate Truststamp's growth in the area of privacy-preserving biometrics, improving its products and services which focus on identity management addressing KYC/AML issues. Previously, he held two data science roles in two distinctive sectors, namely, financial forecasting within an oil and gas industry and modelling, predicting and understanding disease progression from healthcare and health administrative data. Prior to that, he was an associate professor with University of Surrey, during which he published more than 100 peer-reviewed publications, including five best paper awards (AVBPA’05, ICB’09, HSI 2010, ICPR 2010 and Pattern Recognition Journal 2006), and was awarded two personal fellowships sponsored by the Swiss National Science Foundation. He was named the Researcher of the Year by the university of Surrey in 2011. He received his Ph.D. degree in information fusion (machine learning) in 2006 from the Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland. He is currently appointed by University of Malta as an Affiliate Associate Professor.

The European Association for Biometrics is organising a Workshop on the open calls of Horizon Europe that involve biometrics. This event is for member(s) to learn more about the calls, to pitch their ideas and provide networking possibilities.

The selected calls:

• HORIZON-CL3-2021-FCT-01-05: Modern biometrics used in forensic science and by police
• HORIZON-CL3-2022-FCT-01-01: Improved crime scene investigations related to transfer, persistence and background abundance
• HORIZON-CL3-2021-BM-01-03: Improved border checks for travel facilitation across external borders and improved experiences for both passengers and border authorities’ staff
• HORIZON-CL3-2022-BM-01-02: Enhanced security of, and combating the frauds on, identity management and identity and travel documents

• An overview of the objectives of the Border Management and Fighting Crime and Terrorism "destination" provided by the Commission
• The emphasis of each call provided by the Commission
• An opportunity to ask questions about the calls
• An opportunity to pitch your ideas
• Networking opportunities

This will be an EAB members-only event.

Automatic speaker verification (ASV) is among the most convenient, natural and efficient approaches to biometric authentication. Despite the appeal, and like the majority of all biometric systems, ASV is vulnerable to being manipulated by adversaries through spoofing or presentation attacks (PAs). Substantial interest in anti-spoofing or presentation attack detection (PAD) for ASV began only in 2013, with the first competitive challenge known as ASVspoof being held in 2015. Having attracted the participation of 62 independent teams for the 2019 edition, ASVspoof is now one of the largest community-supported anti-spoofing benchmarking challenges. This talk will describe the vulnerabilities of ASV systems to spoofing and PAs, the strategy behind ASVspoof as well as the progress made in the last five years. This shows that the best performing spoofing countermeasures or PAD systems can detect reliably even deepfake synthetic speech or converted voice attacks that humans are incapable of distinguishing from bona fide speech.

Curriculum vitæ

Nicholas Evans is a Professor in Audio Security and Privacy at EURECOM, a Graduate School and Research Centre in Digital Science located in the French Riviera, the Mediterranean coast of southeastern France. His group's research interests include automatic speaker recognition, biometrics and both the security and privacy related implications including anti-spoofing/presentation attack detection, privacy preserving machine learning and anonymisation. He is among the founders of the Automatic Speaker Verification Spoofing and Countermeasures (ASVspoof) and VoicePrivacy community-led initiatives and challenges, is an associate editor of the IEEE Transactions on Biometrics, Behavior, and Identity Science and co-editor of the Handbook of Biometric Anti-Spoofing – Presentation Attack Detection.

We are proud to announce that the European Association for Biometrics (EAB) together with the National Institute of Standards and Technology (NIST), European Union Agency for the Operational Management of Large-Scale IT Systems in the Area of Freedom, Security and Justice (eu-LISA), the ISO/IEC JTC1 SC37 working group 3 is about to organise a workshop to present an update for the latest development on NFIQ 2.1. This update will address through talks and panel discussions the following topics:

• Current production status for NFIQ 2.1
• Experience from stakeholder
• Introduction of training concepts and tools, to retrain the NFIQ 2.0 for other fingerprint images than from optical or inked sources.

The NIST and the ISO/IEC SC37 WG3 are dedicated to adapt and promote the NFIQ2 for large scale biometric systems.

Further information on NFIQ 2.0: https://github.com/usnistgov/NFIQ2

Co-sponsors of this event:

GOLD sponsors of this event:

Sponsors of this event:

This talk will discuss the results of the EU funded project “Towards the European Level Exchange of Facial Images“ (TELEFI project). This project studied how facial recognition is used to investigate crime across EU Member States. In addition, particular consideration was given to the potential for implementing the exchange of facial images within the Prüm framework.

Currently, DNA profiles, fingerprints and vehicle registration data are exchanged within the Prüm framework for combating cross-border crime, terrorism and illegal migration. The Prüm system has been successfully employed for many years and it had reached a point where the introduction of new modalities, including facial images, were considered.

The TELEFI project was conducted by a group of six European institutions: Estonian Forensic Science Institute, Estonian Police and Border Guard Board, Finnish National Bureau of Investigation, Latvian State Forensic Science Bureau, Netherlands Forensic Institute and Swedish National Forensic Centre.

This talk will discuss the administrative and law enforcement use of facial recognition in criminal investigation, will provide a summary of the project, and present the recommendations for the EU Member States.

Curriculum vitæ

Prof. Dr. Didier Meuwly currently shares his time between The Netherlands Forensic Institute (NFI), where he is a principal scientist, and the University of Twente, where he holds the chair of Forensic Biometrics. He specializes in the automation and validation of the probabilistic evaluation and investigation of forensic evidence, and more specifically from biometric traces.

Andra Sirgmets MSc. has received a MSc degree in Molecular Biochemistry from the Tallinn University. From 2008, she has been employed by the Estonian Forensic Science Institute, where she is a Forensic Expert specialised in forensic DNA profiling. She has years of experience working with the Prüm DNA exchange and she has been involved with several research and development projects. During 2014–2015, she was an External Consultant for the United Nations Development Programme. From 2019 until 2021 she was the Project Manager of the EU funded TELEFI project.

As identity is a fundamental right to protect, reliable Biometrics can be key to ensuring this right as long as they are integrated in systems that protect the user’s privacy. IN Groupe develops identity solutions and secure digital services that guarantee this all in providing seamless user experience. This presentation will describe some use cases of these systems and focus on their face biometric functionalities.

The speakers will review key principles that ensure that a face recognition solution is RGPD compliant. They will also describe IN Groupe’s face presentation attack detection solutions. These are essential because presentation attacks can compromise the reliability of biometric data at capture point and therefore threaten the security of the entire system. Solutions achieved have high accuracy and bear the advantage of being passive, meaning that they do not require any specific action from the user.

Curriculum vitæ

Dr. Sandra Cremer holds a Ph.D. in Computer Science from the Institut Mines-Telecom. She is currectly Biometric Research & Development leader within IN Groupe. Previously she was a Biometric Research & Development Engineer for Thales. Dr. Cremer is the author of publications and inventor of patents related to presentation attack detection and iris recognition.

Pascal Janer holds an MBA from the ISG Management School. He is currently VP Sales Europe at IN Groupe with over 20 years of experience in Sales, Marketing and Consulting in large Defense and Security projects, of which 13 years with Thales' C4S Government, Energy and Industry Segment.

From the early days, when security was the driving force behind biometric research, today’s challenges go far beyond security. Machine learning, Image understanding, Signal analysis, Neuroscience, Robotics, Forensic science, Digital forensics and other disciplines, converged in a truly multidisciplinary effort to devise and build advanced systems to facilitate the interpretation of signals recorded from individuals acting in a given environment. This is what we simply call today “Biometrics”.

For the last eighteen years, the International Summer School on Biometrics has been closely following the developments in science and technology to offer a cutting edge, intensive training course, always up to date with the current state-of-the-art.

What are the most up-to-date core biometric technologies developed in the field? What is the potential impact of biometrics in forensic investigation and crime prevention? What can we learn from human perception? How to deploy current Deep Learning approaches? How to deal with adversarial attacks in biometric recognition?

This school follows the successful track of the International Summer Schools on Biometrics held since 2003. In this 18th edition, the courses will mainly focus on new and emerging issues:

• The impact of AI in Biometrics and Biometrics in AI;
• How to make “Deep Biometrics” systems explainable;
• Biometrics for social interactions and emerging applications;
• How to exploit new biometric technologies in forensic and security applications.

The courses will provide a clear and in-depth picture on the state-of-the-art in biometric verification/identification technology, both under the theoretical and scientific point of view as well as in diverse application domains. The lectures will be given by, at least, 18 outstanding experts in the field, from both academia and industry.

An advanced feature of this summer school will be some practical sessions to better understand, “hands on”, the real potential of today’s biometric technologies.

The Norwegian Biometrics Forum (NBF) is an open platform dedicated to regular exchange of information and experience related to the field of Biometrics. The target of the group is the interdisciplinary discussion between research, technology developers, data privacy experts, governmental agencies and operators of Biometric Systems. In the regular meetings new applications, latest research results and products are presented.

Touchless fingerprint recognition represents a rapidly growing field of research which has been studied for more than a decade. Through a touchless acquisition process many issues of touch-based systems are circumvented, e.g. the presence of latent fingerprints or distortions caused by pressing fingers on a sensor surface. However, touchless fingerprint recognition systems reveal new challenges. In particular, a reliable detection and focusing of a presented finger as well as an appropriate preprocessing of the acquired finger image represent the most crucial tasks. Also, further issues, e.g. interoperability between touchless and touch-based fingerprints or presentation attack detection, are currently investigated by different research groups. Many works have been proposed so far to put touchless fingerprint recognition into practise. Published approaches range from self identification scenarios with commodity devices, e.g. smartphones, to high performance on-the-move deployments paving the way for new fingerprint recognition application scenarios. This talk summarizes the state-of-the-art in the field of touchless 2D fingerprint recognition at each stage of the recognition process. Additionally, technical considerations and trade-offs of the presented methods are discussed along with open issues and challenges.

Curriculum vitæ

Jannis Priesnitz received his B.Sc. degree of Computer Science in 2015 from the Hochschule Darmstadt (h_da) for which he was granted the faculty award. He continued studying and received his M.Sc. degree in 2018. Since 2018 he is a Ph.D. Student Member of da/sec at the ATHENE – National Research Center for Applied Cybersecurity (previously CRISP). His current research focuses on touchless fingerprint recognition on mobile and embedded devices.

PriMa (Privacy Matters) is an Innovative Training Network (ITN) funded by the EU through the Horizon 2020 Framework. PriMa is a collaboration between 7 research locations and 7 industrial partner organisations with a focus on the analysis and mitigation of privacy risks in a rapidly digitalising society. One factor contributing to the erosion of privacy is the growth in recognition technologies that not only facilitate the recognition of individuals but also the inference from biometric data of emotional state, gender, health, age, and even profession. Another factor is the fast advancement of artificial intelligence, allowing for extensive data mining, and aggregation, linkage and inference of personal information. Hence, there is a real possibility that acceptable privacy may become unattainable unless technological and societal steps are taken to allow citizens to regain control of their personal information. Therefore, the overall objectives of PriMa are:

• To train 14 creative, entrepreneurial, and innovative researchers as privacy protection experts.
• To contribute to a full understanding of the multidisciplinary nature of privacy protection in a digitalised society.
• To contribute to the development of solutions that address this important societal challenge.

PriMa will train a next generation of researchers to define, investigate and implement solutions that ensure secure and efficient privacy protection whilst keeping the advantages of a digitalised society, and provide them with transferable skills to enable effective planning, management and communication of research ideas and outcomes. This will give them excellent career opportunities.

For more information visit the PriMa homepage.

All times refer to CEST.

IWBF is an international forum devoted to facilitating synergies in research and development among the areas of multimedia forensics, forensic biometrics, and forensic science. State-of-the-art research in areas such as biometrics, forensic science, surveillance, and multimedia forensics will be presented. The 9th edition of IWBF will be a meeting place for those concerned with the use of advanced biometric technologies in forensic applications, attracting participants from industry, research, academia, and end-users.

Topics of interest include, but are not limited to:

• Biometrics
• Attacks to biometric recognition systems
• Multimodal biometrics
• Soft biometrics
• Mobile biometrics
• Biometric analysis of crime scenes
• Forensic Science
• Multimedia forensics
• Integrity verification
• Anonymization & Data Privacy
• Data de-identification
• Surveillance
• Ethical and societal implications
• Information Theoretic Security
• Adversarial Signal Processing
• Case studies on the aforementioned topics

Due to migration, terror-threats and corona-threats various states have re-established border control or even closed the borders. The EAB-members will draft a position paper with suggestions to re-establish free travel between the member states in the Schengen area.

The schedule for the development of the position paper is as follows:

2021-04-28 09.00 to 11.00 brainstorming of ideas

2021-05-02 - deadline for submission of contributions

2021-05-03 16.00 to 18.00 - review of contributions

2021-05-04 - deadline for submission of comments

2021-05-05 10.00 to 12.00 - disposition of comments

2021-05-06 - review of draft paper

2021-05-06 15.30 to 17.00 - finalisation of the paper

Many articles have used voice analysis to detect Parkinson’s disease (PD), but few have focused on the early stages of the disease, the impact of telephonic recordings, and the gender effect. We have adapted the latest speaker recognition system, called x-vectors, in order to detect PD at an early stage using voice analysis. X-vectors are embeddings extracted from Deep Neural Networks (DNNs), which provide robust speaker representations and improve speaker recognition when large amounts of training data are used.

We recorded 221 French speakers (recently diagnosed PD subjects and healthy controls) with a high-quality microphone and via the telephone network. We assessed the impact of the audio segment durations, data augmentation, type of dataset used for the neural network training, kind of speech tasks, and back-end analyses. X-vectors technique provided better classification performances than classical Gaussian Mixture Models for the text-independent tasks, and seemed to be particularly suited for the early detection of PD in women (7 to 15% improvement).

Curriculum vitæ

Dijana Petrovska-Delacrétaz obtained her degree in Physics and her PhD from the Swiss Federal Institute of Technology (EPFL) in Lausanne. She was working as a consultant at AT&T, as a post-Doc at Télécom ParisTech, and as a Senior Scientist in the Informatics Department of Fribourg University, Switzerland. Since 2004 she joined Télécom SudParis as Associate Professor. Her research activities are oriented towards pattern recognition, signal processing, and data-driven machine learning methods, that are exploited for different applications such as speech, speaker and language recognition, very low-bit speech coding, biometrics (2D and 3D face, and voice), crypto-biometrics (including privacy preserving biometrics), and health applications.

The use of biometrics, and in particular the use of fingerprint recognition, is increasing day by day. Not only are we required (in European countries) to capture our fingerprints in order to obtain a passport, but we use them on a daily basis for other tasks such as unlocking our smartphones or confirming a bank transaction or payment.

In spite of the numerous benefits of utilising fingerprint recognition, some drawbacks come with this technology: one does not need to be a tech expert to carry out a presentation attack that may fool a system into believing you are someone else. Unattended capture devices need to have a Presentation Attack Detection (PAD) subsystem, to prevent such attacks.

The workshop raises awareness about this issue and about the current efforts of the biometric community in order to minimise the impact of such attacks. We will thus present a definition of the problem and provide the audience with possible solutions and a look into the future steps.

This workshop will feature presentations by experts from academic, industry, and governmental organisations and will facilitate interactions and discussions between the experts and the audience.

GOLD sponsor of this event:

The European banking ecosystem is a hyper-regulated market, encompassing accounting policy, risk credit, and involving Agencies such as the EBA (European Banking Authority) in Anti-Money Laundering (AML) and counter-terrorism financing actions, on top of the overarching EU DG FISMA.

In parallel, banks are providing financial services that are composed mainly by three offers: banking account, payments means and loans. In this respect all main banks’ activities are impacted by European regulations and by the digitalisation of the society.

Biometrics is now a critical technology empowering several policies to make sure that any customers’ and prospects’ digital identity are secure when entering into:

• Purely on-line on-boarding or enrolment to a new account covered by the AML regulation, also known as “Know Your Customer”.
• Secure electronic authentication to your on-line banking account, covered by the PSDII directive.
• Secure electronic signature when subscribing to on-line services, covered by the eIDAS regulation.
• Secure contactless physical payments.

The event will be centred on policy, standard, technologies and business, around three pillars:

1. Digital Identity and biometrics in the banking world: the Policy landscape.
2. The Biometrics technology challenges of the digital Identity verification.
3. Focus on key topics and challenges.

The speaker roster will include officials from Governmental Agencies, Banking industry practitioners and well as Digital Identity and Biometrics experts. The program will include engaging with an expert panel on current challenges of digital identity verification.

SILVER Sponsor of this event:

Sponsor of this event:

Abstract vector created by vectorjuice - www.freepik.com

With the Covid pandemic, solutions that allow a touchless experience have become increasingly necessary. Biometrics can answer this need by providing the accuracy, speed and ease-of-use required to quickly process people accessing services, crossing borders or requesting a new document

At Thales, it is believed biometrics can help us build a future we can all trust!

During their talk, Daniel Asraf and Jean-Claude Perrin will look at different use cases centred on biometrics, and discuss the challenges of ensuring the system is attack-proof, fast and accurate, in order to protect people’s identity and citizen rights with secure sustainable and user-centric solutions. With the biometric market having undergone years of development, they will look back at what has been achieved, and explain how deep learning can help advance biometrics even further.

Curriculum vitæ

Dr. Daniel Asraf holds a Ph.D. in Statistical Signal Processing and Electrical Engineering from Uppsala University.

He serves as Vice President of Public Security and Biometrics Business for Thales Digital Identity & Security, and was previously the Head of R&D for 3M Cogent. Prior to it, he served as Director of Algorithm and Embedded Development for Bioscrypt, L-1 Identity Solutions and Director of Engineering for Safran Morpho. He has also worked for McGill University and the Swedish Defense Research Agency.

Dr. Asraf is the author of multiple peer-reviewed publications on optimal detection theory, and inventor of detection and classification related patents.

Jean-Claude Perrin holds a Master degree in Business Administration (IAE Paris), and graduated from the Ecole Centrale de Lyon. He also holds Executive Education Management degrees from INSEAD and Berkeley.

He serves as Vice President Strategy and Marketing of the Identity & Biometric Solutions Business Line at Thales Digital Identity & Security. In his 20 years of career in the digital identity & security domains, Jean-Claude has always been working on challenging cutting-edge topics in various international marketing, sales and business management positions.

He is also a founder and the Secretary General of the Secure Identity Alliance, which supports sustainable worldwide economic growth and prosperity through the development and adoption of secured digital IDs and electronic services.

Sagem mobiles introduced the fingerprints for mobile phones in 2010. The integrated fingerprint sensors on mobile phones have since inspired a wide variety of applications that include mobile banking. Despite the commercial success, the solutions were criticized in early stage for poor presentation attack detection algorithms. The subsequent generation of solutions have not only focused on the other biometric modalities such as face and ocular region, but have proposed better solutions for presentation attack detection and privacy protection. Today, a wide range of solutions are provided for presentation attack detection and privacy protection one can choose from.

This talk will present and discuss major milestones for biometrics on smartphones for banking applications. It will summarize the research achievements in the last decade, commercial success and few challenges to be addressed in near future. A particular focus will be given on approaches and solutions proposed within SWAN project (funded by Research Council of Norway) for various smartphone based biometric authentication in the light of banking applications.

Curriculum vitæ

Kiran Raja obtained his PhD in Computer Science from the Norwegian University of Science and Technology (NTNU) in 2016. He is faculty member at Dept. of Computer Science at NTNU, Norway. His main research interests include statistical pattern recognition, image processing, and machine learning with applications to biometrics, security and privacy protection. He was/is participating in EU projects INGRESS, SOTAMD, iMARS and other national projects such as SWAN. He has authored several papers in his field of interest and serves as a reviewer for number of journals and conferences. He is a member of EAB where he co-chairs the Academic Special Interest Group.

Algorithmic decision systems have frequently been labelled as “biased”, “racist”, “sexist”, “unfair” by numerous media outlets, organisations, and researchers. Are such assessments justified? Should citizens and policymakers be concerned? What is the current state of the research? How can variation across demographic groups be quantified in evaluations of such systems? These and other related matters have recently become a hot topic in the context of biometric technologies, which are ubiquitous in personal, commercial, and governmental applications. Biometrics represent an integral component of many surveillance, access control and operational identity management systems, thus directly or indirectly affecting billions of people all around the world.

The EAB organizes a series of virtual events with “Demographic fairness in biometric systems” as an overarching theme. The events will feature presentations by experts from academic, industry, and governmental organisations and will facilitate interactions and discussions between the experts and the audience.

The goal of the events is to raise awareness, define the problem and propose solutions and possible next steps.

A white paper will be published based on the outcomes of the virtual events.

GOLD sponsor of this event:

sponsor of this event:

Until about 2015, there was only one dominant fingerprint technology for law enforcement applications: Optical sensors based on total reflection. In recent years, many new technologies have entered the market and have enabled new applications for fingerprint acquisition. This presentation explains the technical basics of these technologies, compares them with each other, and gives an outlook on future trends and their challenges.

Curriculum vitæ

Dirk Morgeneier graduated with Master degrees in theoretical electrotechnics as well as image processing.

He is the co-founder of JENETRIC GmbH, the experts in digital fingerprint capturing. In his position as CEO, he has been responsible for developing new technologies and products since 2014, and is known as a successful technology influencer in the industry.

For more than 20 years Dirk has been working in the biometrics industry. His ideas and developments have shaped the market over the past two decades, with a proven track record for first-in-class products. He is the man behind the well-known tenprint scanner "Guardian" and pioneer of the 1000 ppi fingerprint and palm devices. The latest innovation: by using optical transparent TFT sensors to capture fingerprints, Dirk and his team have overcome the barriers of previous technologies.

Workshop of the Biometrics Working Group of TeleTrusT, the IT Security Association in Germany

Deeply-learned face representations enable the success of current face recognition systems. Despite the ability of these representations to encode the identity of an individual, recent works have shown that more information is stored within, such as demographics, image characteristics, and social traits. This talk will show that many more soft-biometric attributes are embedding in face templates and that these attributes often have a strong correlation on the face verification performance.

Curriculum vitæ

Philipp Terhörst completed his studies in physics at the Technical University of Darmstadt in 2017. Since then, he has been working in the Smart Living & Biometric Technologies department at the Fraunhofer Institute for Computer Graphics Research (IGD) as a researcher. His research interest includes research at machine learning and biometric solutions focusing on quality assessment, privacy-enhancement, and bias-mitigation in face recognition. He is author of several publications in conferences and journals such as CVPR and IEEE Access and is regularly serving as a reviewer (e.g. for TPAMI, TIP, PR, BTAS, ICB). For his scientific work, he received several awards such as the EAB Biometrics Industry Award 2020 from the European Association for Biometrics for his dissertation or the IJCB 2020 Qualcomm PC Chairs Choice Best Student Paper Award. Moreover, he was involved in the Software Campus program, a management program of the Federal Ministry of Education and Research (BMBF).

Ten years back in spring 2011 our Norwegian Biometrics Laboratory (NBL) was established and for the opening we organized a workshop. Since then we have celebrated the NBL Annual Workshops (NBLAW). All the workshops are listed on the NBL homepage.

Our 10 years celebration will have a modest character due to the ongoing COVID-19 situation. But nevertheless we would like to (virtually) spend the day together with our friends and inform the public about the research that we conduct. Thus the theme of the NBLAW-2021 is "Face Morphing Attack Detection".

Widespread deployment of Automatic Border Control (ABC), along with electronic Machine Readable Travel Documents (eMRTD) for person verification, has enabled a prominent use case of face biometrics in border control applications. The trust anchor are biometric passports. Many countries issue eMRTD passports on the basis of a printed biometric face photo submitted by the applicant, a procedure which allows the possibility of the photo being either altered to beautify the subject’s appearance or morphed to conceal his/her identity. If an eMRTD passport is issued with a morphed facial image, two or more data subjects can then use it to pass a border control. This workshop will present discuss the morphing attack problem and indicate early solutions to detect such morphed facial images.

All times refer to CET.

In its first part the presentation will cover the increasing usage of live enrolment for German ID cards and passport since 2012: although live enrolment has not been made mandatory in Germany for a long time, Speed Biometrics GmbH has equipped over 100 local authorities (including more than 40 % of all large cities) in 11 federal states with over 180 Speed Capture systems during recent years.

The second part will deal with the attempt of the German Ministry of the Interior, Building and Community to make live enrolment mandatory and the resulting final law adopted by the German Bundestag end of 2020 (defining a dual approach allowing the applications to choose between a passport photo captured and transferred digitally by photographer and using live enrolment equipment at the authority where available).

The third part of the presentation will be dedicated to the (possible) consequences - challenges and chances - arising from the aforementioned law becoming effective 2025.

Curriculum vitæ

Stefan Pahmeier has been heading the realization of Speed Capture as the first live enrolment solution for German ID cards and passports. He has become managing director of Speed Biometrics in 2015. As such he is continuously working on improving the current solution to meet evolving technical requirements as well as customer demands. He has followed the legislative procedure resulting in the above mentioned law very closely.

The presentation will deal with the methods of fingerprinting, digitization and processing for the creation of fake fingerprints (PAD), the extraction of features (minutiae) and their use for generating synthetic fingerprints, including damage simulation. Last but not least, the fingerprint damage detection and its origin and overall quality estimation of the fingerprint will be mentioned.

Curriculum vitæ

Prof. Martin Drahansky graduated in 2001 from the Faculty of Electrical Engineering and Computer Science BUT and simultaneously from the Faculty of Electrical Engineering FernUniversität in Hagen, Germany. His Ph.D. thesis was focused on generating cryptographic keys from fingerprints, which he defended in 2005 at the Faculty of Information Technology BUT. In 2017 he was promoted to full professor. He worked from 2002 to 2005 at the University of Siegen, Institute of Measurement Technology (Germany) and also collaborated with the Fraunhofer Institute for Computer Graphics Research IGD in Darmstadt (Germany). In 2014, he went on sabbatical to the Tokyo Institute of Technology (Japan) for half a year. In recent years, he has focused on areas related to biometric systems – processing of images and videos, sensoric systems (including embedded systems and robotics) and IT security. During his leisure activities he practices judo, mountain bike, via ferratas, fitness and mineralogy plus entomology.

The team of the Department of Multimedia Systems of the Gdańsk University of Technology in Poland has been working with the largest Polish bank in the field of biometrics since 2015. They have constructed an experimental multimodal biometric workstation replicated in 100 copies and installed in 60 branches of this bank. This workstation allowed them to conduct a large experiment in which they investigated the usability of different banking biometric modalities. The biometric system includes a biometric pen the team constructed to verify handwritten signatures, a camera and their proprietary facial recognition software, a microphone that works with an artificial neural network to verify the speaker, and a hand-vein sensor.

The team at GUT involved over 150 bank advisors and nearly 10.000 bank customers in the experiment. Also, they used surveys to gather opinions on the usefulness of the different types of biometrics. They have currently constructed an upgraded testbed, which has been extended with a scanner of ID documents and a gaze tracker, enabling contactless control of the whole biometric authentication process, and it also provides yet another biometric modality based on the analysis of saccadic movements.

In their video footage presentation, Prof. Czyżewski will talk about their construction work, research, results, and work in progress.

Curriculum vitæ

Prof. Andrzej Czyżewski is the Head of the Department of Multimedia Systems of the Gdańsk University of Technology in Poland. His scientific interests focus on multimedia techniques and their numerous interdisciplinary applications for telemedicine, traffic control, smart cities, biometrics, and others.

Prof. Czyżewski lectures at the Gdańsk University of Technology on "Multimedia technologies" and "Sound and image engineering." He cooperates with, among others with the Medical University of Gdańsk and with some large international corporations, with the PKO Bank, with the General Directorate of National Roads and Motorways, and with many smaller enterprises in which he and his team implement inventions and innovations being developed. He is the author of over 600 scientific publications and nearly 30 patents. He has so far promoted 13 doctors (Ph.D.) and over 300 masters of science (M.Sc.) and engineers.

This talk will cover the iris presentation attack detection. With a backbone based on two survey papers on this topic recently co-authored by Czajka (published in ACM Computing Surveys, 2018 and in Pattern Recognition Letters, 2020), Czajka will primarily discuss the problem of recognition of unknown attack types (unseen during training), or less popular attack types (such as cadaver eyes), and will bring a few ideas of making the iris PAD algorithms more attack type-agnostic. A short summary of available iris PAD datasets, open-source iris PAD solutions, and the performance in an open-set classification regime observed in the fourth edition of LivDet-Iris competition (concluded in 2020) will be delivered.

Curriculum vitæ

Adam Czajka is an Assistant Professor in the Department of Computer Science and Engineering at the University of Notre Dame. His research focuses on biometrics and security, especially on human-driven methods of detecting unknown types of presentation attacks driving a biometric system into incorrect decision. In general, he is fascinated by wide spectrum of research topics in computer vision, pattern recognition and machine learning. Recently, he has been exploring the use of visual signals generated by artificial neural networks in stimulation of emotions and mental healing processes. In the classroom, he enjoys teaching graduate- and undergraduate-level Computer Vision (CSE 40535/60535/40536/60536), Biometrics (CSE 40537/60537) and Neural Networks (CSE 40868/60868) courses.

Czajka is originally from Poland. He received M.Sc. in Computer Control Systems (hons), Ph.D. in Biometrics (hons) and D.Sc. degree ("habilitation") in Computer Science, all from Warsaw University of Technology (WUT). Before coming to Notre Dame, he was the Chair and co-founder of the Biometrics and Machine Learning Laboratory in the Institute of Control and Computation Engineering at WUT, the Head of the Postgraduate Studies on Security and Biometrics, the Vice Chair of the NASK Biometrics Laboratory, and the Chair of the Polish Standardization Committee on Biometrics. He is a Senior Member of the IEEE, an active member of the EAB, an associate member of the IAI and an expert of ISO/IEC Sub-Committee 37 on Biometrics.

The xAI4Biometrics Workshop aims at promoting a better understanding, through explainability and interpretability, of currently common and accepted practices in several and varied applications of biometrics. These applications, in scenarios comprising identity verification for access/border control, watching lists surveillance, anti-spoofing measures embedded in biometric recognition systems, forensic applications, among many others, affect the daily life of an ever-growing population.

The xAI4Biometrics Workshop @ WACV 2021 will include five oral paper presentations and two keynote talks:

• "Explaining Deep Neural Network Decisions for Enhanced Biometric Systems" by Prof. Peter Eisert (Humboldt University Berlin and Fraunhofer HH)
• "At the Two Extremes of Interpretability in Machine Learning: Very Sparse Models and Interpretable Deep Neural Networks" by Prof. Cynthia Rudin (Duke University).

You are still on time to register and remotely attend, not only the workshop but also the WACV2021 conference for a very affordable fee.