Electroencephalography (EEG) is the recording of electrical activity along the scalp. EEG measures voltage fluctuations resulting from ionic current flows within the neurons of the brain [1]. A number of published research papers have indicated that there is enough individuality in the EEG recording, rendering it suitable as a tool for person authentication. In recent years there has been a growing need for greater security for person authentication and one of the potential solutions is to employ the innovative biometric authentication techniques. In this research paper, we investigate the possibility of person identification based on features extracted from person’s measured brain signals electrical activity (EEG) with different classification techniques; Radial Basis Functions (RBF), Support Vector Machines (SVM) and Backpropagation (BP) neural networks. The highest identification accuracy was achieved using modular Backpropagation neural network for classification