Eye tracking system

Abstract

This report describes the design and development process of a brain-computer interface (BCI) based eye tracking system which provides locked-in patients a different way of communication through eye movement. The eye tracking system is developed using C++ programming language and utilized OpenCV library. It is able to continuously track and determine the target buttons being activated. Steady state visual evoked potential (SSVEP) concept is being integrated to the system by implementing a flickering stimulus in order to increase the reliability and robustness of the system. Ten healthy undergraduates participated in the validation of the system. Validation results showed a system accuracy of 91.25%. It achieves better performance as compared to the past system developed. The new eye tracking system has the advantages of being low cost, ease of operation, requires little training and can be personalized to any iris colour.