Upcoming Events

In this talk, In this talk, Richard Guest, Eva Lievens and Martin Sas will discuss the future of Facial Age Estimation.

Automated facial age estimation systems provide technology-based solution for verifying or attributing a person’s age from a facial image. Whilst it is important to enhance the technological performance of systems, it is vital that deployment is considered across disciplines, encompassing legal, ethical, sociological, and technological spheres and, importantly, the interface between them.

In this talk, the presenters will assess:

• The current range of the deployment of systems and the future application demands of the technology,
• The legal and regulatory framework within which the technologies operate and
• Future research and development questions and requirements for robust, fair, and ethical use of systems

Curriculum vitæ

Richard Guest is Professor of Biometric Technologies at the University of Southampton, UK. He is an appointed member of the UK Home Office Biometrics and Forensics Ethics Group advising the UK Government on the use of biometric technologies. His research interests include mobile technologies, age estimation, testing and ethical use and explainability.

Eva Lievens is an Associate Professor of Law & Technology at Ghent University, Belgium. She researches the legal impact of technology design and deployment, human and children’s rights in the digital environment, and alternative regulatory instruments to regulate tech phenomena.

Martin Sas is a doctoral researcher at the Centre for IT and IP law (CiTiP) at KL Leuven, Belgium and is financed by the FWO PROGRRES project. Martin explores a wide range of topics, including data protection regulation and children's rights, age-appropriate designs, behavioural designs and dark patterns, age verification systems, privacy-enhancing techniques, and risk management methodologies.

We thank our media partner:

The International Standard ISO/IEC 29794-5 Biometric sample quality - Part 5: Face image data was recently published. Along with this new standard the source code of the Open-Source Face Image Quality (OFIQ) software library was provided, which is the reference implementation of this standard.

The standard defines a unified quality score (UQS) for a face image and numerous, component quality measures (CQM), which provide accurate information such as the correctness of the pose or the sharpness of the face image (and many others).

This virtual meeting will provide an overview of the functionality provided with OFIQ and will give users an opportunity to raise questions and provide feedback.

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

We thank our media partner:

The 12^th edition of the EAB Research Projects Conference is organised by the European Association on Biometrics (EAB)

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 70 participants from academia, industry and public institutions.

We thank our media partner:

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

EAB Academy presents this training by Patrick Grother, delving on performance aspects across the biometric lifecycle; from enrollment, attack detection, duplicate detection, quality analysis through to the authentication, and one-to-many identification.

Drawing insights from NIST’s biometric evaluations, the session will address the drivers of recognition failure: detection, quality, ageing, compression, twins and demographic effects, active attack, and the human role. The training will cover recent standards, performance testing generally including the roles, strengths, and weaknesses of the various kinds of biometric evaluation, and the use of synthetic data.

NIST has been the foremost evaluator of biometric technologies for almost a quarter of a century. As an independent government laboratory, its frequent, public, and large-scale face, fingerprint, iris, and speech technology evaluations have been credited with driving recognition accuracy forward. The performance metrics that NIST formulated are today incorporated in ISO/IEC 19795 standards and used across industry. Moreover, these benchmarks have revealed key aspects about the technology, for example in face recognition templates as small as 300 bytes are highly accurate, twins remain a problem, sublinear search duration is possible without loss in accuracy, and false positive rates vary considerably across demographic groups.

EAB is launching the 19th 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.

Sponsor of this event:

We thank our media partner:

The BIOSIG 2025 conference addresses current issues in the area of biometrics and will present innovations and best practices that can be transferred into future applications.

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.

We thank our media partner:

The EAB in collaboration with Research institute CODE and Idiap is organising a second workshop on Biometric Template Protection!

The Biometric Template Protection (BTP) research field has been developing steadily for over two decades, with many innovative solutions having been proposed in this time. As a result of rising concerns around the privacy and security of our biometric data, which is being increasingly demanded for identity management in practical applications, today there appears to be renewed interest in BTP research. This may be attributed to recent and emerging privacy regulations, which are pressuring practitioners to ensure that their biometric systems are legally compliant with the enforced privacy requirements.

There is thus a clear opportunity and a pressing need to explore the BTP research field further, to investigate its practical relevance and to gauge the potential of BTP solutions for achieving more secure and privacy-preserving biometrics-based identity management. During the EAB Workshop on BTP, we will present a clear picture of the progress made thus far, both in the development of different types of BTP schemes and in their Standardised evaluation. We will also discuss the challenges that remain to be tackled.

The proliferation of voice deepfakes and adversarial attacks presents an increasing challenge to the security and reliability of voice-based authentication and communication systems. While deepfake technology enables the generation of highly realistic synthetic speech, adversarial attacks exploit vulnerabilities in machine learning models to manipulate or evade detection systems. Both threats pose significant risks to biometric security and the overall trustworthiness of AI-driven applications.

This workshop will feature presentations by experts to explore recent advancements in detecting and mitigating both voice deepfakes and adversarial attacks. Discussions will focus on deep learning-based countermeasures, adversarial robustness techniques, generalisation across unseen attacks, and the evolving nature of attack strategies.

We thank our media partner:

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

We thank our media partner: