Software that can turn any smart phone into an eye-tracking device is developed by researchers led by an Indian-origin scientist. It is a discovery that can help not only in psychological experiments but also in marketing research. The system could enable new computer interfaces or help detect signs of incipient neurological disease or mental illness along with making existing applications of eye-tracking technology more accessible.
A graduate student in electrical engineering and computer science at Massachusetts Institute of Technology, Aditya Khosla explained that since there are no applications, there’s no incentive for people to buy the devices. We thought we should break this circle and try to make an eye tracker that works on a single mobile device, using just your front-facing camera. Using machine learning, a technique in which computers learn to perform tasks by looking for patterns in large sets of training examples Khosla and his colleagues from MIT and University of Georgia built their eye tracker. Khosla said currently, their training set includes examples of gaze patterns from 1,500 mobile-device users.
Khosla explained, that for assembling data sets, most other groups tend to call people into the lab. He added that it is really hard to scale that up. Calling 50 people in itself is already a fairly tedious process. But we realized we could do this through crowd sourcing. Researchers were able to get the system’s margin of error down to 1.5 centimetres by using training data drawn from 800 mobile-device users. They enrolled application users through Amazon’s Mechanical Turk crowd sourcing site and for each successfully executed tap they were paid a small fee. At the Computer Vision and Pattern Recognition conference in Las Vegas on June 28 the team will describe their new system.
