Abstract: The aim of this paper is to present a system for controlling the cursor position in a computer by human eye movements. The developed system uses a two-axis voltage measure obtained by an infrared light reflection procedure to determinate the cursor position into a computer screen. Two approaches are compared, an algorithmic approach using polynomials and an artificial neural network (ANN) one. Because of the nonlinear relation between voltage and cursor position, the use of an ANN is a good solution to solve this problem. An additional advantage of ANN is an incremented flexibility. Tests show that both methods obtain similar results.
Authors: Alberto Molina, Iñigo Monedero, Carlos León, Isabel Gómez, José Manuel Elena.
Paper in Artificial Intelligence Applications (International) in Málaga, Spain at 2002.
Publication: IASTED INTERNATIONAL CONFERENCE ARTIFICIAL INTELLIGENCE AND APPLICATIONS.
ISBN: 0-88986-352-0
[gview file=”https://grupo.us.es/ustic150/wp-content/uploads/2010/10/EYE.pdf”]
[gview file=”https://grupo.us.es/ustic150/wp-content/uploads/2010/10/PresentaciónAnima.ppt”]