The study based on transient visual evoked potentials is a kind of way to study brain-computer interface

and the key is the study on recognition algorithm of transient visual evoked potential.The accumulation averaging and wavelet filter method are used to extract VEP signal from the background full of noise.PCA are used to extract the feature of VEP signal.KNN is used to recognize the feature signal.The correct recognition rate reaches 95 % when EEG come from three people.The experimental results show that the method can recognize transient visual evoked potentials more correctly.