Towards Automatic Retrieval of Blink-Based Lexicon for Persons Suffered from Brain-Stem Injury Using Video Cameras

  1. (PDF, 291 KB)
AuthorSearch for:
ConferenceProceedings of the First IEEE Computer Vision and Pattern Recognition (CVPR) Workshop on Face Processing in Video, June 28, 2004., Washington, District of Columbia, USA
AbstractDirectly connected to the brain, the eyes are the last part of our body we lose control of. For some persons, such as those suffered from a brain-stem stroke, the eyes provide the only means of communication with the world. The eye blinks for such persons are used to make their lexicon and the goal of many rehabilitation centers worldwide is to build tools that would allow automatic detection of the eye blink based lexicon. The tools designed so far are very cumbersome and still do not show the desired performance. At the same time, recent advances in computer hardware and computer vision, in particular, in motion and change detection, offered practitioners a new way for detecting blinks based on video observations of the person's face. This paper overviews different techniques to the problem and describes a vision-based system which is presently being tested in one of the rehabilitation centres. We show how to reliably detect a two-eye blink with a help of an off-the-shelf web-camera and present an approach to the detection a single-eye blink (wink) - this type of blinks is much harder to detect due the lack of spacial constrains, it is however the only type of movement some patients can exhibit.
Publication date
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NRC number47138
NPARC number8914335
Export citationExport as RIS
Report a correctionReport a correction
Record identifier3f098d22-2509-4319-8237-94b83f3fff9a
Record created2009-04-22
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)
Date modified: