Face Recognition from a Tabula Rasa Perspective

Abstract

In this paper a system for face recognition from a tabula rasa (i.e. blank slate) perspective is described. A priori, the system has the only ability to detect automatically faces and represent them in a space of reduced dimension. Later, the system is exposed to over 400 different identities, observing its recognition performance evolution. The preliminary results achieved indicate on the one side that the system is able to reject most of unknown individuals after an initialization stage. On the other side the ability to recognize known individuals (or revisitors) is still far from being reliable. However, the observation of the recognition evolution results for individuals frequently met suggests that the more meetings are held, the lower recognition error is achieved