Air Canada is experimenting with digital ID with facial recognition

Avatar photo

Air Canada is the first airline in the country to introduce digital ID, using facial recognition technology.

As part of an ongoing pilot project, digital ID is now available for passengers departing from Vancouver International Airport and arriving on select flights to Winnipeg, as well as for passengers entering Air Canada Coffee at Toronto Pearson International Airport.

Eligible customers will receive an invitation to use the fingerprint identification option and instructions on how to create their secure fingerprint before arriving at the airport.

Learn more about facial recognition

Many people are familiar with facial recognition through the use of FaceID to unlock iPhones (and that’s just one use among many). Generally speaking, facial recognition does not rely on a huge database of photos to determine a person’s identity: it only identifies and recognizes a person as the sole owner of the device, to prevent others from have access to it.

Beyond unlocking phones, facial recognition works by comparing the faces of people walking past special cameras to photos of people being monitored. These spied lists can contain photos of anyone, even people who have never done anything wrong, and the photos can come from anywhere, even social media accounts. Facial recognition systems can vary, but they generally work like this:

Step 1: face detection

The camera detects and locates the image of a face, alone or in a crowd. The image can show the person from the front or in profile.

Step 2: face analysis

Next, an image of the face is captured and analyzed. Most facial recognition technologies use 2D rather than 3D because it is more convenient to compare a 2D image to photos or images in a database. The software analyzes the geometry of the face. Key factors include the distance between the eyes, the depth of the eye sockets, the distance between the forehead and the chin, the shape of the cheekbones, as well as the outline of the lips, ears and chin. The goal is to identify the specificities of your face.

Step 3: convert image to data

The face capture process transforms the analog information (a face) into a set of digital information (the data) according to the characteristics of the person’s face. In fact, the analysis of your face is transformed into a mathematical formula. The digital code is called a face print. In the same way that fingerprints are unique, everyone has their own facial imprint.

Step 4: find a match

Your face print is then compared to a database with other known faces. For example, the FBI has access to nearly 650 million photos on numerous state databases. On Facebook, photos with identified people join their database which can also be used for facial recognition. If your facial print matches an image in the database used by facial recognition, a match is made.

Facial recognition is considered the most natural biometric measure. Which makes sense on an intuitive level, because we recognize ourselves and others by looking at the face, rather than fingerprints or irises. It has been determined that more than half of the world’s population is affected by facial recognition technology on a regular basis.

Catherine Mills Avatar