Stéphane Gentric (Research unit manager, IDEMIA) animera le séminaire du13 octobre.
2D Face Recognition is one of the oldest computer vision application. As techniques improve, more complex databases arise, always leaving space for algorithm improvements. This lecture will review the whole face recognition pipeline, how early methods address the main issues and how Deep Learning handles them now. We will present major operational deployments and the most recent performances. Finally, we will discuss current limitations and future research avenues.
Stéphane Gentric is Research Unit Manager at Idemia and Associate Professor at Telecom Paris. He obtained his PhD on Pattern Recognition at UPMC in 1999. As principal researcher, then team leader, he worked on Fingerprint recognition algorithms, then Face, then Iris and now also Video Analytics. As Senior Expert, he was involved in most of Idemia’s biometrics projects over the past 15 years, such as the Changi border crossing system as well as NIST benchmarks, or the UIDAI project. His current research interests are focused around pattern recognition for the improvement of biometric systems.