[Passenger Terminal World] Accurate Recognition
Challenging
for change
CUBOX, a face
recognition and biometrics provider, has scored the best result in the latest
National Institute for Science and Technology Facial Recognition Vendor Test
(NIST FRVT) for face recognition accuracy in Paperless Travel category, which
simulates real-life use of airports and passenger boardings. CUBOX’s face
recognition algorithm was found to have a non-match rate of only 0.3 percent in
matches against a database of 42,000 templates. This latest test
concerns a specific application one-to-many matching in airport settings, where
travelers’ faces are matched against a database of individuals who are all
expected to be present. NIST looked at whether technology could be viable
elsewhere in airport, specifically in the security line where perhaps 100 times
more people might be expected during a certain time window. The successful results follows an update
of its top scoring facial recognition algorithms for the 1:N Identification,
1:1 Verification and Face Mask Effects tests.
Rise of
Passenger Experience
CUBOX deployed a
new generation of its automated border control (ABC) e-Gates, as well as replace old models
in South Korean airports and harbors.
The project launched by the Korean government, aims to standardize the interface and middleware
systems of border control gates. This will, in turn, facilitate the maintenance
and support of the biometric border solutions across the country. It is expected to upgrade the Domestic and International
travel processes of Korean airports with “seamless immigration procedures”. The
improved immigration efficiency is expected to help prepare border control
points for the return to normal volumes of air traffic.
In addition, CUBOX has been providing the Korean government with
biometric e-gates since 2013, with over 200 e-Gates already deployed across all
international airports in the country.