Electroencephalogram (EEG) signal presents a great potential for highly secure biometric systems due to its characteristics of universality, uniqueness, and natural robustness to spoofing attacks. EEG signals are measured by sensors placed in various positions of a person's head (channels). In this work, we address the problem of reducing the number of required sensors while maintaining a comparable performance. We evaluated a binary version of the Flower Pollination Algorithm under different transfer functions to select the best subset of channels that maximizes the accuracy, which is measured by means of the Optimum-Path Forest classifier. The experimental results show the proposed approach can make use of less than a half of the number of sensors while maintaining recognition rates up to 87%, which is crucial towards the effective use of EEG in biometric applications.