ABSTRACT: Eye gaze tracking (EGT) systems have been implemented previously in laboratory environments. However, they present usability obstacles that prevent their broad commercial acceptance. In response, a cursor control system was created that integrates an electromyogram-based control with EGT-based control. This system allows a user to perform small cursor displacements and left click operations by the monitoring and classifying of electromyogram (EMG) signals emitted during facial movements. This functionality will compensate for the limitations in cursor positioning accuracy and in click execution reliability experienced with EGT systems.
The EMG/EGT system, an EGT system and a mouse were tested using point-and-click trials. Trial time and error rate results underwent statistical and Fitts’ law analyses. Statistical analysis revealed that the EMG/EGT system was slower than the two other inputs, but was significantly less error-prone than the EGT-only system. Fitts’ law analysis showed that the EMG/EGT system was not well matched with Fitts’ model.