Face Recognition Workshop London
FACE RECOGNITION WORKSHOP, TUESDAY 16 OCTOBER, 1.30PM - 5.00PM
This workshop takes place the day prior to the Biometrics Congress on 17-18 October 2018 as part of Biometrics Week London
PRESENTERS: Patrick Grother and Mei Ngan, NIST
Patrick Grother is a scientist at the National Institute of Standards in Technology responsible for biometric standards and testing. He leads the IREX, FRVT and FIVE evaluations of iris and face recognition technologies that support biometrics in national scale identity management. He co-chairs NIST’s International Biometrics Performance Conference on measurement, metrics and certification. He edits the biometrics specifications for the US Government's PIV credentialing program, for which he received his second Department of Commerce Gold Medal. He assists a number of US Government agencies on research, development and evaluation, and serves as editor of several ISO standards - he received the IEC 1906 Award in 2009 and the ANSI Lohse IT Medal in 2013.
Mei Ngan is a scientist at the National Institute of Standards and Technology (NIST). Mei received the B.S. degree in computer engineering from the University of Maryland, College Park in 2003 and the M.S. in computer science from the Johns Hopkins University in 2006. Her research focus includes evaluation of tattoo recognition and face recognition technologies. Mei has authored and co-authored several technical publications, including outcomes from large-scale evaluation of one-to-many face identification algorithms, performance of facial age and gender estimation algorithms, and publication of a seminal open tattoo database for developing tattoo recognition research, which she received the Special Contribution Award for at the 2015 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA).
The workshop will cover face recognition performance including gains from the new generation of algorithms, demographic effects, ageing, and other results from the NIST Face Recognition Vendor Tests (FRVT). Target audience is end-users, integrators, application developers and others interested in the technical performance aspects of face detection and recognition.
State of the industry
- Face recognition in 2018: Technologies, applications, providers, platforms
- Face recognition gains 2000 – 2018: A Revolution
- Where’s the challenge?
NIST Activities – Now and Near Term
- FRVT 1:N 2018 – results from the largest biometric test ever conducted
- FRVT 1:1 – ongoing assessment of face recognition
- FRVT MORPH – face morphing detection
- IJB – a set of open-book recognition challenges with wild images
- Face image quality – putting face capture on par with fingerprint and iris
- IFPC 2018 – factors in applied and operational face recognition
Face recognition performance and measurement
- Algorithms – comparison of latest prototypes
- Imagery – mugshot, visa, wild, twins, sketches, disguise
- Demographics – differential impacts of gender, age, race
- Ageing – as driver of policy
- Gallery composition – population size, historical images, consolidation vs. not
- Resource consumption – sizes, speeds, complexity
- Human roles and capabilities
Hunting down face recognition errors
- Nature versus capture
- Image quality and standardization
- Passive vs. active problems
Member: £200 + VAT = £240
Non Member: £400 + VAT = £480
BECOME A MEMBER AND SAVE
Become a member now to take advantage of the reduced rates.
The Biometrics Institute provides training and course material as a tool to help you conduct due diligence. While the Institute has used reasonable care to ensure the accuracy of the material and course, due to the content and variable inputs during and after the process of implementing biometrics, the Institute cannot be held accountable for outcomes or compliance. The material and course have been prepared for informational purposes only and are not intended to provide legal or compliance advice. You should consult your legal advisor should you require advice on the legal or compliance aspects of the material or course.