Face recognition and related psychological phenomenon have been the subject of neurocognitive studies during last decades. More recently the problem of face identification is also addressed to test the possibility of finding markers on the electroencephalogram signals. To this end, this work presents an experimental study where Brain Computer Interface strategies were implemented to find features on the signals that could discriminate between culprit and innocent. The feature extraction block comprises time domain and frequency domain characteristics of single-trial signals. The classification block is based on a support vector machine and its performance for the best ranked features. The data analysis comprises the signals of a cohort of 28 participants.