The Market Monitor Minding the Nation's Business
Boston—Scientists are developing a new mobile software that can accurately identify where a person is looking in real time, an advancement that may lead smartphones, tablets and other mobile devices to be controlled by eye movements.
In an effort to make eye-tracking cheap, compact and accurate enough to be included in smartphones, researchers are crowdsourcing their collection of gaze information and using it to “teach” the mobile software how to figure out where a person is looking.
The researchers at the Max Planck Institute for Informatics in Germany, the Massachusetts Institute of Technology (MIT), and the University of Georgia have, so far, been able to teach the software, named iTracker, to identify where a person is looking with an accuracy of about a centimeter on a mobile phone and 1.7 cm. on a tablet.
“It’s still not exact enough to use for consumer applications,” said Aditya Khosla, a graduate student at MIT, of the software.
However, he believes the software’s accuracy will improve with more data.
The technology has been expensive, and has required hardware that made it tricky to add the capability to mobile gadgets.
It could make eye-tracking a lot more widespread, and also helpful as a way to let users play games or navigate their smartphones without having to tap or swipe on them.
The researchers started out by building an app called GazeCapture that gathered data about how people look at their phones in different environments outside the confines of a laboratory.
The user’s gaze was recorded with the phone’s front camera as they were shown pulsating dots on a smartphone screen.
To make sure they were paying attention, they were then shown a dot with an “L” or “R” inside it, and they had to tap the left or right side of the screen in response.
GazeCapture information was then used to train iTracker. The handset’s camera captures the user’s face, and the software considers factors like the position and direction of his head and eyes to figure out where his gaze is focused on the screen.
“About 1,500 people have used the GazeCapture app so far,” Khosla said, adding that if the researchers can get data from 10,000 people, they will be able to reduce the software’s error rate to half a centimeter, which should be good enough for a range of eye-tracking applications. PNA/PTI