An Eye Tracking Computer User Interface

Arie E. Kaufman, Amit Bandopadhay and Bernard D. Shaviv
Computer Science Department
State University of New York at Stony Brook, NY 11794-4400


We developed an inexpensive hardware software system for eyetracking. It is based on electro - oculography (EOG) rather than expensive reflectance based methods. We built a prototype to demonstrate the viability of EOG for human - computer communication. The system is applicable for many virtual reality systems, video games, and for the hadicapped.

Hardware Components

4 EOG sensing channels

Signal filters to eliminate noise

Signal amplifiers

A/D converters


This project has been supported by a grant from the New York State Science and Technology Foundation and by National Science Foundation grant IRI-9008109. We wish to express special thanks to George Piligian, MD, for his help with this project.

Software Modules

Classification and filtering of EOG signal

Extraction of symbolic tokens

Graphical user interface

EOG Placement

Experimental Results

  • A 3x2 boxed menu driven by eye selections
  • Performance measures of correct selections recorded after repeated use by two experienced users

Menu Selections 73%
Menu Selections (4 corners only) 90%
Horizontal Detection 75%
Horizontal Detection (4 corners only) 99%
Vertical Detection 92%
Vertical Detection (4 corners only) 92%