That's what a Danish startup called Senseye claims to be doing; they say they've got software for Android that uses the front-facing camera to track a user's eye movement and then uses that to control what happens on the phone's screen. They're not alone in working on doing that kind of work, either. Eye tracking could be a big new way that users interact with their devices.

First there was the command line for controlling computers, then there was the Graphic User Interface - now there's the NUI. A natural user interface is defined as a human-computer interface that is transparent or invisible. It's exciting but just beginning to be explored. Eye tracking as NUI? Apple has been rumored for several years to have licensed Tobii technology for tablet use, but it's not clear that such use would really work very well.

It seems a little hard to believe that the same level of detailed control over a cursor that you can get from your finger touching the screen can be captured by watching your eyes, but Senseye says it works and it's winning European startup awards. Blogger Martin Bryant profiled the company on The Next Web last night and posted the video you can also watch below.

Robert Stevens, CEO of THiNK Eye Tracking, wrote an in-depth post almost two years ago about the challenges that eye tracking technology faces before it can enter consumer markets like this. The biggest issue is that eyes move around a lot, they need to in order to see, but they are far harder to track accurately than fingers touching a screen.

Let's assume it really works though. I don't know if you're really going to keep it running all the time so it can catch you peeking at your phone and turn it on, for example. I'm also not sure that eye movement is really going to be a faster system of input than the options we've already got. Maybe it's just different and appropriate for different circumstances.

I never understood speech interfaces either until I was riding my bike down a street a few weeks ago, unsure of the exact address of the business I was headed to. I pulled out my iPhone, launched the Google App and said its name. The address popped right up and biking while talking to your phone is less risky, I suppose, than other types of input.

Most of the time speech input is slow, imprecise and socially awkward but it clearly has its place, like when you're in transit.

Tobii introduced its own eye-tracking video game last month, too. Asteroids, it seems, is a particularly good use case. Angry Birds? We'll see. Stevens of THiNK Eye Tracking called Tobii's game "Brilliant PR" but emphasized that "eye control is of little practical utility for most people in most situations."

In response to Stevens' critical comments, Tobii UX designer Joakim Isaksson offered the following in a LinkedIn thread last month.

"When eye tracking first starts making its way into the mainstream market, it will simply complement current methods of user input, such as mouse, keyboard, touch and voice. My favorite example of this so far is a nifty feature we have developed called MouseWarp, where the mouse cursor jumps to where you are looking when you start moving it towards your point of regard. It's extremely simple, but especially when used in conjunction with a trackpad on a laptop it is also very powerful. [See this prototype Tobii eye tracking system for controlling a Lenovo laptop which made an appearance this Spring.]

"As the market matures, we will start seeing computers and devices that anticipates what you want to do, for example pre-loading content when you look at something instead of when you click it. As for computer games, eye tracking makes it possible for the game world to react to your gaze; imagine walking in to a bar in GTA7 and when you accidentally gaze at the dodgy guy in the corner he flips out and pulls out his baseball bat. On top of that, graphics rendering can be made more intelligent; why render everything on screen with full Vertex count and Anti-Aliasing, when you're only really looking at 1 % of it at any given time?

"There are countless other possibilities that eye tracking enables, and most of them have yet to be discovered."

The Read/Write Implications

There's certainly a lot of gee-whiz going on here, but there are also read/write implications to consider. If eye tracking can prove a faster, more efficient way to do some things on computers, then that could mean those things get done more often. It's nice to think about the human eye being an active participant in media, not just a passive recipient of broadcast messages. If I could sort assets, navigate large maps or otherwise interact with large quantities of information with my eyes, I think I would do more sorting of information.

Is sorting a form of writing? I don't know that it is, but I don't think eye tracking is likely to facilitate richer input than that.

But it's probably a mistake to think of eye tracking happening in isolation. Used in conjunction with multiple other forms of input, like touch, mouse, sensors, keyboards, etc. it could be a great asset to a more complex set of user interface options.

Newspaper readers finished articles slightly quicker than iPad readers, who were more likely to skim content than to read it fully. Newspaper readers also had better retention, with 90% remembering what they read on paper compared to 70% of users of the iPad. See some of their videos after the jump.

Here is the video of eye-tracking with an iPad:

And a physical newspaper:

Google did some eye-tracking research of its own in 2009 and found that most users stayed on the top of the page when viewing search results and followed an F-shaped pattern down the page.

For developers, publishers and advertisers looking to get some user experience information through eye-tracking, a startup called YouEye can provide eye-tracking through Web cams. The startup was at the LAUNCH conference in February and is still in beta.

Feng-GUI has been around for awhile -- it was pitched on the TechCrunch forums to little reaction over a year ago -- but just recently the company released the results of a test that it says proves the accuracy of its algorithm. According to the company, Feng-GUI attention maps capture 70% of what traditional eye and mouse tracking report -- or, in other words, they are 70% as accurate. Because the work is being done by a computer rather than humans, one has to assume that it is cheaper.

The visual results of the test are impressive -- Feng-GUI does indeed seem to stack up well to traditional eye tracking. But because the methodology of the study, who did it, and how it was conducted wasn't released, it is hard to trust it.

There is, however, one major problem with Feng-GUI: I couldn't get it to work. The heat map generator on the Feng-GUI page timed out on every attempt to generate a map for ReadWriteWeb (it supposedly times out after 30 seconds, but RWW has loaded quickly all day), or any other web site I tried. Nor could I get it generate a map for a screenshot of ReadWriteWeb that I uploaded.

Google's Portuguese site as seen by Feng-GUI.

Regardless, I do like the idea of Feng-GUI. If the algorithm can be trusted, it has a lot of useful applications for designers and web site owners. The service could theoretically be used for testing early stage prototypes of new designs without having to pay people to perform usability studies or exposing half-baked new ideas to beta testers. Or it could be used by advertisers to figure out which display ad would attract the most attention on a specific web site before making an ad buy. Theoretically, sites could even use data from the service to charge more for a specific ad spot based on visual attention rather than higher click-thru rates (though selling advertisers on a robot's opinion might be a bit of a tall order).

What do you think of the idea of eye tracking vs. click tracking? What about algorithmic pseudo-eye tracking? Could you get Feng-GUI to work for you? Leave your thoughts in the comments below.