Brain computer interface systems are capable to detect and interpret the mental activity into computer interpretable signals giving opportunity for performing computer controlled activities without muscular movement. An challenging area in Brain Computer Interface research is the classification of EEG signals using the raw signals captured which has to undergo some preprocessing, so that the right attributes for classification are obtained. In this paper, we propose to extract the energy component of the EEG signal by processing the data in the frequency domain using Discrete Cosine Transform and application of classification techniques. The proposed method has very good classification accuracy compared to research already carried out in this area.