Eye-Blink Detection System for Human-Computer InteractionBy Krolak, Aleksandra; Strumillo, Pavel; Universal Access in the Information Society,
Publication Date: October 2, 2011
Paper presents a vision based human-computer interface (HCI) developed for severely paralyzed users. The interface detects voluntary eye blinks and interprets them as control commands. The employed image processing methods include Haar-like features for automatic face detection and template matching based eye tracking and eye blink detection. The interface is based on a notebook equipped with a typical web camera. It is designed for Windows OS and has the following functionalities: (1) loading and navigating web pages, (2) controlling the mouse cursor and emulating keyboard and mouse keys, (3) text entry, and (4) turning off the computer. Interface performance was tested with 49 users, of which 12 had physical disabilities. Test results indicated interface usefulness in offering an alternative means of communication with computers. The users entered English and Polish text with at an average speed of 12 seconds per character and were able to browse the Internet. The interface application, named b-Link, is available online as open source software at http://www.sourceforge.net/projects/b-link/.
Published by: Springer Publishing Company (Website:http://www.springerpub.com)
Link to text: http://www.springerlink.com/content/t21596614163182u/fulltext.html