Eye Tracking for Mobile Control
By Grifantini, Kristina; Technology Review,Publication Date: May 24, 2010
Article features a new eye-tracking system that lets a user operate a smart phone with eye movement. Developed by researchers at Dartmouth College, EyePhone operates by means of an algorithm that learns to identify a person’s eye under different conditions. During a learning phase, the system is trained to identify a person’s eye at varying distances and under different lighting. The user calibrates the system by taking pictures of the left and right eye both indoors and outdoors. EyePhone, which runs on a Nokia 810 smart phone, tracks the position of an eye relative to the screen. To select an application, the user moves the phone slightly so the icon is directly in front of the eye and then selects the application by blinking. According to researchers, the system is at least 76 percent accurate in daylight and when the user is stationary, and 60 percent accurate when the person is in motion.
Published by: Technology Review, Inc. (Website:http://www.technologyreview.com)
Massachusetts Institute of Technology (MIT) (Web Site: http://www.mit.edu )
Link to text: http://www.technologyreview.com/computing/25369/?nlid=3015&a=f
Link to audio: http://www.audiodizer.com/technologyreview/computing/25369.mp3
