At IFSEC International 2017, pioneering facial recognition specialist Aurora will unveil its latest next-generation technology development: FaceSentinel LR, a long-range sensor that extends Aurora’s industry-leading near infrared capabilities to a wider range of distances, making it suitable for applications such as queue management, surveillance, and VIP identification. The specialist biometric imaging and illumination technology is designed to work with the latest versions of Aurora’s Deep Learning-based Facial Recognition engines.
Aurora is established as a world leader in ‘near IR’-based facial recognition, and has logged millions of successful events in applications including time and attendance, airport passenger management and access control. Now FaceSentinel LR uses high speed global shutter technology and a high brightness near IR ceramic flash to deliver a series of HDR still frames to Aurora’s facial recognition engine. Dynamic image analysis provides for adjustment of the illumination to optimise the clarity of a subject’s face in the next frame, repeatable at up to 40fps.
Aurora Head of Sales and Marketing Gary James says FaceSentinel LR addresses the issues found in operating facial recognition with visible light CCTV images, a major obstacle for accuracy in situations where the subject isn’t presenting their face directly to a camera.
“This problem has been overcome by integrating the specialist illumination and imaging components in one application-specific device,” James says. “The sensor is highly compact, with very low power consumption, despite its powerful output and processing ability. This extends the operational range of our IR face recognition capability fivefold, opening up many new applications such as queue monitoring and covert identification.”
Fastlane Glassgate 300 turnstile
Aurora will also show its FaceSentinel Sensor integrated with the Fastlane Glassgate 300 turnstile, operating in both token-free “Identification” Mode (1:n), which allows registered users access simply by looking at the sensor, and in “Verification” Mode (1:1), which adds a biometric layer to the functionality of any access control system. In Verification mode, FaceSentinel confirms the identity of a person holding a card or entering a PIN, before passing the details through to the access control system. Both authentication and verification happen in a second or less.
FaceSentinel is the world’s first biometric access control authentication product powered by Deep Learning
FaceSentinel is the world’s first biometric access control authentication product powered by Deep Learning; the system uses AI and infrared light to achieve unparalleled facial recognition speed, accuracy, and reliability. Aurora’s facial recognition technology is – among other places - used throughout Heathrow Airport for boarding pass verification and in British Airways’ domestic self-boarding gates.
Deep Learning is a pioneering technique used to create a highly optimised Artificial Intelligence. It works by first creating a blank “brain”: an artificial neural network. This brain is then trained to recognise faces by presenting it with millions of face image examples, enabling it to become more experienced, faster, and more accurate at the facial recognition task than any human or existing technology could be.
Integrated Design Limited (IDL) is the designer and manufacturer of Fastlane Turnstiles and Door Detective anti-tailgating products, and has over 30 years of experience and a worldwide distribution and installation network.
At IFSEC International 2017, FaceSentinel and FaceSentinel LR will be running on IDL’s stand E1550.