Facial Recognition Technology in Changi Airport T4

Singapore’s Changi Airport Terminal 4 uses facial recognition technology to offer self-service options.

The technology is used at check-in, bag drop, immigration and boarding, providing authentication for each passenger’s identity by essentially comparing the portrait on a digitised biometric passport with the holder’s face.

By automating the processes and checks for the departure journey, what results is an enhanced airport experience for passengers who will encounter shorter queues and greater flexibility to check-in at their own convenience. There is also greater security for passengers and improved productivity for staff who can be redeployed to take on other roles, such as to identify suspicious characters in the airport.

###How is Facial Recognition deployed? A photo of the passenger is captured at Terminal 4’s automated bag-drop counter and matched against his or her photo in the passport before the luggage is accepted and moved into the baggage handling system. The passenger’s photo is taken again at the automated immigration gates, which uses a dual facial and thumbprint recognition system. Again, this will be matched against the photo in the passport. Before boarding the aircraft, the passenger can use the automated boarding gate by scanning his or her boarding pass and a photo will be snapped. The facial recognition system matches this photo against the one taken at the immigration gate before letting the passenger through the gate.

###What’s the science behind facial recognition technology?

Facial recognition technology is a popular biometric benchmark as it is easy to deploy and implement without need for physical interaction. More critically, face detection and face matching processes for verification or identification are very fast. From the captured photo, facial recognition systems generate a faceprint which is unique to a single individual. The unique faceprint is a data set generated through algorithmic code, from precise measures such as the distance between the eyes, distance from the forehead to chin, the bridge and width of the nose, contour of the lips or ears, and length of the jaw line. A facial recognition system will typically check between 75 to 85 points in a face to build a faceprint or pattern. This faceprint can then be used to search through a biometric data base for matches, which under controlled scenarios, with close to 99% accuracy. The faceprint is a good solution to avoid storing images and allows for greater security and privacy.

###Looking ahead Changi Airport will continue leveraging on the use of facial recognition on a larger scale for its three older terminals, and additionally to help locate passengers who get lost in the sprawling airport terminals, or those spending a little too much time in the duty-free shops. This will lower the incidences of flight delays or missed flights, and strengthen Changi Airport’s competitiveness as Asia Pacific’s leading airhub.

An additional video for more information: Video on the technologies in Changi Airport’s Terminal 4