Thanks to a competitive private sector, Facial Recognition is entering the mainstream. Where can we expect this revolutionary technology to go next?
When Apple CEO Tim Cook announced the iPhone 8 on September 12, one new feature garnered more press than any other – the option to allow users to unlock the phone and authenticate payments using facial recognition technology. While rival Samsung already has this feature in its Galaxy 8, Apple claims to have taken it to the next level by including both a primary sensor and an infrared sensor for in-the-dark facial recognition. Early reports from users indicate that the technology could be a game-changer, with some tech bloggers making the bold claim that it’s “light-years beyond anything that’s been tried commercially.” Is that really the case, or is it just marketing hype? What can we expect next in the realm of FR technology? To answer these questions (and many others), we need to take a short “whistle-stop” tour of FR’s history to see where it originated and how far it’s come, have a look at the existing options on the market and see how they work, and sneak a peek at alternatives to FR that might inspire it to get better.
In the Beginning
The story of Facial Recognition software begins over half a century ago. In the 1960’s, Woody Bledsoe, Helen Chan Wolf, and Charles Bisson worked together to teach the primitive computers of the era to recognize human faces. However, because the funding for their work was provided by an unnamed intelligence agency that did not allow publicity, very little of the work was published. The technology came into its own in the 1990s, and once again it was the United States Government that was the driving force. In 1993, the Defense Advanced Research Projects Agency (DARPA) and the National Institute of Standards and Technology rolled out the Face Recognition Technology (FERET) program to encourage the commercial face recognition market. The project involved creating a database of 2,413 still facial images representing 856 people. The hope was that a large database of test images for facial recognition would inspire the kind of innovation that would lead to more powerful facial recognition technology.
The Long Arm of the Law
It worked. Not surprisingly, law enforcement agencies and the U.S. government were the first to explore the possibilities of the new technology, and the National Institute of Standards and Technology (NIST) began Face Recognition Vendor Tests (FRVT) in the early 2000s. Building on FERET, FRVTs were designed to provide independent government evaluations of both commercially available facial recognition systems and prototype technologies.
An Explosive Debut
In terms of taking the technology commercial, Samsung got out of the gate first, packing advanced facial recognition technologies inside their Galaxy Note 7. Unfortunately, that model’s battery issues and tendency to burst into flames gathered more attention than the technology inside it, but the FR technology stuck around for the Galaxy S8 and the new Note 8, and forms part of Samsung’s security suite alongside fingerprint options. Samsung’s iris scanning technology works by identifying the patterns in human irises. Like fingerprints, these are unique to every individual, making them almost impossible to duplicate. However, the system hasn’t proven quite foolproof – it can be tricked by highly detailed prosthetic eyes.
Android Flies Under the Radar
There’s a good chance you’re not aware of it, but Android has been able to unlock your phone with your face for years now. Not every manufacturer chooses to implement it, but many smartphones can and have been making use of this feature (which Android calls “Trusted Face”) for quite some time. Unfortunately, the technology is obsolete by now – it might be a convenient way to unlock your phone, and it doesn’t involve extra hardware, but its accuracy is entirely dependent on the quality of a phone’s front camera. What’s more, the image processing time can be quite slow on older phones – not great in an emergency when you need to unlock your phone in a hurry! The lack of any sophisticated hardware also leaves it more prone to exploitation, even with simple photographs of your face. Neither Google nor Samsung advertise it as a secure way to protect your phone, and neither company’s engineers recommend it over the use of a PIN.
The Apple Way
Apple went back to the drawing board and took a different approach with its Face ID, which is designed to map out a user’s entire face. The iPhone X uses an infrared flood light to illuminate a face, at which point a secondary 30,000-point infrared laser matrix is beamed out to reflect off the flood light. An infrared camera then detects subtle changes in the matrix point reflections as your face makes tiny movements, which allows the camera to capture accurate 3D depth data. In theory, the only way to “hack” this system would be to either have an identical twin or make a very accurate prosthetic face. Either way, the jury is still out as to whether Face ID is more secure than Samsung’s iris scanner.
Anil Jain, a Michigan State University professor who studies biometric recognition and computer vision, says it’s very possible that smartphones will eventually include sensors for face, iris, and fingerprint recognition. The cost isn’t that high for the hardware, he reasons, and a user might want to use them in different combinations for different transactions – you might decide which you want to use, or for a big purchase on the phone, you might want to use all three. “There is no reason why all three can’t be in your mobile phone within the next few years,” he says.