Abstract
Human computer interaction systems via eye blinks have been reported. A purpose of these systems is communication aid for people with severe physical disabilities, such as amyotrophic lateral sclerosis (ALS) patients. Some of these systems classify user's voluntary (conscious) blinks. If the voluntary blinks can be distinguished in automatic, the usability of the input interface is increased. We have proposed an eye blink extraction method that utilizes split interlaced images of the eye. These split images are odd- and even- field images and are generated from interlaced images. The proposed method yields a time resolution that is double that in the 1080i Hi-Vision format. We refer to this approach as a “frame-splitting method”. We realized a method for automatic eye blink extraction using frame-splitting method. Based on this extraction method, we also proposed a classification method of a blink type which set a threshold in the duration of eye blink. Our classification method requires calibration process before measurement. In this paper, we clarify required minimum number of eye blinks for the calibration. Furthermore, we discuss the performance of blink type classification using this calibration.
