EOG-based eye movements codification for human computer interaction

This paper describes a new eye-control method for eye-based computer interaction using EOG. This work aims to resolve some of the problems encountered in current systems when used for long periods of time and users become tired. For this purpose, a new electrooculographic eye model based on wavelet transform and neural networks is proposed. The results obtained demonstrate the system’s reliability in detecting eye movements and show an error of less than 2° during long periods of use. The system proposed may be used to control any graphical interface using eye movements detected by electrooculography.