Computer Science
A real-time vision interface based on gaze detection - EyeKeys
Document Type
Book Chapter
Abstract
There are cases of paralysis so severe the ability to control movement is limited to the muscles around the eyes. In these cases, eye movements or blinks are the only way to communicate. Current computer interface systems are often intrusive, require special hardware, or use active infrared illumination. An interface system called EyeKeys is presented. EyeKeys runs on a consumer grade computer with video input from an inexpensive USB camera. The face is tracked using multi-scale template correlation. Symmetry between left and right eyes is exploited to detect if the computer user is looking at the camera, or to the left or right side. The detected eye direction can then be used to work with applications that can be controlled with only two inputs. The game "BlockEscape" was developed to gather quantitative results to evaluate EyeKeys with test subjects.
Publication Title
Real-Time Vision for Human-Computer Interaction
Publication Date
2005
First Page
141
Last Page
157
ISBN
9780387276977
DOI
10.1007/0-387-27890-7_9
Repository Citation
Magee, John J.; Betke, Margrit; Scott, Matthew R.; and Waber, Benjamin N., "A real-time vision interface based on gaze detection - EyeKeys" (2005). Computer Science. 48.
https://commons.clarku.edu/faculty_computer_sciences/48
APA Citation
Magee, J. J., Betke, M., Scott, M. R., & Waber, B. N. (2005). A real-time vision interface based on gaze detection—EyeKeys. Real-Time Vision for Human-Computer Interaction, 141-157.