Abstract
In our previous studies, an eye control input interface using an electrooculograph EOG amplified by ac coupling has been developed. We proposed an eye gesture input interface using a combination of several eye movements. It is unnecessary for eye gesture input to restrict head movement, in contrast to conventional eye gaze input. However, it is necessary to use a start operation before eye gesture input. Therefore, eye glance input has been proposed. Eye glance input uses only a combination of eye movements in opposite directions, so that it does not need start operations. However, eye glance input has not always been successful because the algorithm for detection of eye movement from EOG signals was not adapted to slight shifts of the signal baseline. In this study, we propose a new determination algorithm for the eye glance input interface. In experiments using our improved algorithm, we achieved direction determination success rates of over 80% for six subjects.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call