Machine Infers Person's Interests from His Eye-Movement
From: Aalto University - 12/16/2010

Researchers at Aalto University have developed technology that retrieves
information from data glasses about people and objects the viewer is looking
at. The system makes use of an eye tracker and machine-learning methods to
enable it to infer from the context and gaze direction what the viewer may be
interested in. The technology can display additional information on the
viewer's data glasses and infers when to display additional information by
following eye movements. The machine retrieves information from a database
developed by the researchers, but it also can be set to display information
from the Internet and social media. However, such searches can only be made
by looking through the data glasses. Also, the system can only recognize
people whose images have been entered into the database. "Our basic research
on machine-learning methods has made it possible to create new advanced user
interfaces in which the machine infers without direct human commands what the
viewer is interested in," says Aalto professor Samuel Kaski. 

Read the entire article at:
http://www.aalto.fi/en/current/news/view/2010-12-16-003/

Links:
Visual directed browsing
http://www.youtube.com/watch?v=gtuGSWDVdQU

Photos with augmented reality views
http://www.flickr.com/photos/35622531@N08/tags/uiart/

Urban contextual information interfaces with multimodal augmented reality
http://mide.tkk.fi/en/UI-ART

An Augmented Reality Interface to Contextual Information
http://research.ics.tkk.fi/mi/papers/vire10.pdf

Samuel Kaski
samuel.kaski@hiit.fi