An Eye Tracker in Every Smartphone?

Eye Tribe wants to make eye tracking cheap and easy—as long as you don’t wear bifocals

2 min read
An Eye Tracker in Every Smartphone?

I’ve tried eye tracking technology before, most recently at this year's mega Consumer Electronics Show, where Tobii Technology has for a couple of years demonstrated its latest advances. Computers that respond to the movements of the users eyes are, of course, invaluable for folks who can’t use their hands. But they may go mainstream, because, like curb cuts, they can also be useful for those who don’t need assistive technology.

Eye trackers let you scroll a long document with a phone in one hand and a cup of coffee in the other. They haven't, at least to date, helped much when it comes to selecting buttons on the screen, which, when it works at all, takes too much time and concentration. It's just easier to touching a button on the display itself or a mouse. But they are very cool for playing the kind of games in which you blow things up in space—you feel like you have a superpower when you can zap the person who pushed past you on the sidewalk just by glaring at them (as I discovered; see the video above).

Eye Tribe, a startup that launched at Demo Mobile this week, says its Mobile Eye Control works on the same principle as Tobii’s technology—it sends out a beam of infrared light and uses its reflection to locate the pupils in a user's face. It works well, even if you're wearing eyeglasses, though it can be confused by bifocals.

Unlike Tobii, Eye Tribe says, it is not using special chips to process the eye tracking data. Instead, it’s relying on the processors already in a mobile device. That means, the company says, it can be built into mobile devices for just a couple of dollars. While Eye Tribe will be building and selling its technology as a peripheral as part of a developer’s kit, it hopes to convince mobile device manufacturers to include the hardware as standard in mobile devices, and license Eye Tribe’s software to enable eye tracking.

Follow me on Twitter @TeklaPerry.

The Conversation (0)

The Future of Deep Learning Is Photonic

Computing with light could slash the energy needs of neural networks

10 min read

This computer rendering depicts the pattern on a photonic chip that the author and his colleagues have devised for performing neural-network calculations using light.

Alexander Sludds
DarkBlue1

Think of the many tasks to which computers are being applied that in the not-so-distant past required human intuition. Computers routinely identify objects in images, transcribe speech, translate between languages, diagnose medical conditions, play complex games, and drive cars.

The technique that has empowered these stunning developments is called deep learning, a term that refers to mathematical models known as artificial neural networks. Deep learning is a subfield of machine learning, a branch of computer science based on fitting complex models to data.

Keep Reading ↓ Show less