Idiap Research Institute to host tutorials on spoofing, BEAT platform
The Idiap Research Institute announced it is hosting a tutorial on spoofing and anti-spoofing during the International Conference on Biometrics, held in Phuket, Thailand on May 19-22.
The tutorial will be delivered by Sébastien Marcel, a senior researcher at Idiap Research Institute.
He will discuss the main research outcome of the TABULA RASA (Trusted Biometrics under Spoofing Attacks) project, a European funded project (7th Framework Program) that addresses issues of spoofing attacks on trusted biometric systems.
The tutorial will discuss the methodology for the evaluation of vulnerabilities to spoofing attacks, the vulnerability to spoofing attacks (2D face, 3D face, near infrared, iris, fingerprint and voice), anti-spoofing tactics, lessons learned from the anti-spoofing competitions, lessons learned from the ICB Spoofing Challenge in 2013, and future work.
Attendees do not require any specific knowledge other than a general understanding of biometrics technologies.
The Idiap Research Institute is also offering a tutorial on the BEAT platform during the eleventh IEEE International Conference on Automatic Face and Gesture Recognition, held in Ljubljana, Slovenia.
The tutorial will present the BEAT platform for online reproducible research, providing the introduction of new concepts and hands-on experience.
The BEAT platform allows novice and advanced researchers to benchmark systems and components, run comparative evaluations, certify toolchains, provide educational material for newcomers in pattern recognition, and optimize algorithms and systems.
All of these tasks can be done without installing additional software on the user’s computer as the BEAT platform operates exclusively from the web browser.
The tutorial will discuss the motivation, requirements and design of the BEAT platform, the existing components of the BEAT platform, registered user interaction, the addition of new components to the BEAT platform, and the future of the BEAT platform.
The tutorial is intended for both beginners and advanced researchers of any computer vision field that are interested in reproducibility, experiment longevity and software re-use.