Automatic removal of eye-blink artifacts based on ICA and peak detection algorithm

In this study a novel technique is proposed to automatically remove eye-blink artifacts from EEG signals. EEG signal is decomposed into independent components by independent component analysis (ICA) method. First, we demonstrate that feature-extraction method is not very suitable for identifying eye-blink artifacts components. Hence a peak detection algorithm of independent component is proposed to identify eye-blink artifacts components. Finally, the proposed artifact removal method is evaluated on some contaminated EEG signals, and the results show that it is able to effectively remove eye-blink artifacts from EEG signals with little distortion of underlying brain signals.