28pm1-E-1 Recognition of eye's movement and condition for user interface by using transparent eye tracker

Abstract

We propose a wearable line-of-sight detection system that utilizes micro-fabricated transparent optical sensors on eyeglasses. These sensors can detect the difference of reflection light intensity between white of eye and pupil. Up until now, we successfully have detected all directions which based on 4 directions (up, down, right, left and), blink by using the proposed system. Our system showed experimentally that the error is as small as 1.5°. In order to develop practical application of our system, we improved our system to detect more precise conditions: open eye, blink, close eye. We finally devised an algorithm which converts these 3 conditions to the input signals.