Dr. Sébastien Marcel
Senior Research Scientist
Idiap research institute
1920 Martigny, Switzerland
Sébastien Marcel received the Ph.D. degree in signal processing from Université de Rennes I in France (2000) at CNET, the research center of France Telecom (now Orange Labs). He is currently interested in pattern recognition and machine learning with a focus on multimodal biometric person recognition.
He is a senior research scientist at the Idiap Research Institute (CH), where he leads a research team and conducts research on face recognition, speaker recognition and spoofing attacks detection.
In 2010, he was appointed Visiting Associate Professor at the University of Cagliari (IT) where he taught a series of lectures in face recognition.
He serves on the Program Committee of several scientific journals and international conferences in pattern recognition and computer vision.
Sébastien Marcel is the principal investigator of international research projects including MOBIO (EU FP7 Mobile Biometry), TABULA RASA (EU FP7 Trusted Biometrics under Spoofing Attacks) and BEAT (EU FP7 Biometrics Evaluation and Testing).
On the importance of benchmarking in facial image analysis
Benchmarking is a sensitive issue in the facial image analysis research community. It is a requirement for scientific publications but unfortunately it lacks precise standards and hence rely mostly on common practices. As a consequence, it is very often difficult or almost impossible to reproduce published research results because of the absence of open source code or open databases or open experiment configurations. We will then discuss current practices. Nevertheless, many efforts have been made to foster reproducible research in facial image analysis with their advantages and limits. In this talk, we will review former competitions/challenges, benchmarking tools and databases used in large-scale International research projects (M2VTS, BANCA, MOBIO, TABULA RASA, BEAT). Finally, we will present a initiative geared toward solving possibly the above issues.