Electrooculogram identification from eye movement based on FIR system
Tasawan Puttasakul, Komkrit Archawut, T. Matsuura, Pitak Thumwarin, Surapan Airphaiboon · 2016
In this paper, we propose a method for detecting eye movements based on EOG signal. The EOG signal can be process separately through horizontal and vertical channel from the surface muscle around the eye. This method consists of 2 main processes; feature extraction and classification. Feature extraction is implemented from DCT coefficients of the EOG signals and impulse response of FIR system. The FIR system can fully characterize the inherent eye movement by considering the DCT coefficients as the input and output, respectively. The eye movement can be detected by evaluating the Euclidian distance. The minimum Euclidean distance for each eye movement uniquely occurs at a distinct Euclidean distances between reference impulse response and extracted features by FIR system. The experimental results show that the proposed method is useful for identifying eye movements.