Epileptic seizure detection in EEG recordings using phase congruency

This paper presents the use of phase congruency to robustly detect the epileptic seizure. Phase congruency is calculated from log Gabor wavelets. Numbers of spikes detected from the phase congruency of two classes of EEG data (epilepsy and seizure free) are used as the features of interest. By using only one dimensional features, the detection accuracies of the proposed method are comparable with the existing magnitude-based methods.