July 17, 2013 -
This widely reported research outlines a system for eye-tracking that uses infrared light and cameras. Light reflects off the surface of the eyeball and is picked up by the camera. Based on the idea that everyone’s eyes move uniquely, the system can verify users ambiently. The team recently presented its study at the Internatinoal Associateion for Pattern Recognition’s International Conference on Biometrics in Madrid.
By the sounds of it, this modality falls into one of biometric identificaiton’s grey areas, as this is a behavioral measurement. Similar to keystroke dynamics or gait recognition, these systems indeed can identify us from others, but samples are gathered ambiently and are based on an activity, rather than only a single, static sample (fingerprint image, facial scan etc.).
“The goal of eye-tracking signatures is to enable inexpensive cameras instead of specialized eye-tracking hardware,” Lead researcher Cecilia Aragon said. “This system can be used by basically any technology that has a camera, even a low-quality webcam.”
This isn’t the first time eye-tracking has entered the biometric discussion, though authentication is a somewhat new application in this vein.
Reported previously, Emotient, which specializes in facial expression analysis, and iMotions, an eye-tracking and biometric software platform company, have announced a newly integrated platform that combines facial expression recognition, eye-tracking, EEG and GSR technologies, designed primarily for usability and market research and neurogaming.
Also, the Biometrics Research Group has said that it expects technologies that track eye and gesture movements to play a large role in future mobile applications and devices. Samsung’s new Galaxy smartphone features this technology.