Facial Recognition in Gambling

Casinos are some of the earliest adopters of facial recognition, using the technology to identify known card counters, criminals or those in voluntary exclusion programs. As the technology becomes more refined, we see its adoption across more realms.  How exactly does it work?  What are the concerns? How could a lottery use it?

How Facial Recognition Works

Facial recognition is the process of identifying or verifying the identity of a person using their face. It captures, analyzes and compares patterns based on the person’s facial details.

By using biometrics to map facial features, it verifies identity through key features of the face. The most key feature is the geometry of a face, such as the distance between a person’s eyes and the distance from their forehead to their chin, creating what is called a facial signature.  This mathematical formula is then compared to a database of known faces. This is all achieved using an artificial intelligence technique called machine learning.

Face recognition allows us to both identify and verify. Identification answers the question: “Who are you?”, whereas authentication answers the question: “Are you really who you say you are?”.

With recent advances in facial recognition algorithms, recognition accuracy is getting much better and thus leading to the wider adoption of the technology.

Of course, other signatures via the human body also exist such as fingerprints, voice recognition, digitization of veins in the palm, iris scans, and behavioural measurements. However, facial recognition is the easiest to deploy and implement, as there is no physical interaction required by the end-user.

Challenges with the Technology

Naturally, security and privacy are a big issue.  We witnessed this earlier this year with the release of FaceApp, an app which takes your photo and ages it to show what you’ll look like in a few decades. It was later realized that it was owned by a questionable Russian company and suspicions grew as to if they were capturing these images for purposes of surveillance.

In addition, despite the technology having improved 20-fold in a four-year span, it is not without faults. Some examples of faulty recognition:

– Holding a photo or a video up to a camera has been known to fool the technology

– Some facial recognition solutions struggle to differentiate between twins

– Lighting and other cosmetic changes can prevent a person from being accurately identified

– Can be inaccurate at identifying people of colour, especially black women.

– A new beard or weight gain can make a person unrecognizable.

AI is superior to humans in facial recognition in ideal environments such as airport check-ins, where the face is straight on and it is well-lit and the camera is high-quality.  In poorer circumstances, with the camera looking down, it is poorly-lit and lower-definition – it is far less effective.

Facial Recognition In the Lottery Industry

Know Your Customer (KYC) has been a hot topic this past year and for some companies, facial recognition has reduced KYC review times from hours to minutes.

Using biometric technology in its payment app, Bacta, the trade association for the amusement and gaming machine industry in the UK, aims to help operators align with age verification requirements, as well as promoting safer gaming and data minimization. The technology enables users to prove their age without revealing their date of birth or providing any additional personal data, drawing on a dataset of many thousands of photos tagged with verified ages.


If you’d like to know more about Genera Networks or the products and services we offer, please contact Vanessa Garro Peeters at vanessa.garro-peeters@generanetworks.com



Contact Us

If you would like to know more – send us an email and we'll get back to you!