ACTIVE FACE RECOGNITION WITH A HYBRID APPROACH

The automatic detection of person's identity is a very interesting iss ue both in social and industrial environments. In this paper a system for automatic identity recognition from face images, is presented. The proposed approach is based on an hybrid iconic approach, where a firs t recognition score is obtained by matching a person's face against an eigen-space obtained from an image ensemble of known individuals. The hypothesis is then verified by computing the correlation of the gray level histogram of the new face image with the histograms of the subje cts in the database,A selective attentional mechanism is applied to re duce the amount of information needed to describe a database of human faces. This is accomplished both at the task level, by performing plan ned fixations, and at the sensor level, by adopting a space-variant sa mpling of the images, By using a space-variant image geometry, the siz e of the database is considerably reduced and consequently also the pr ocessing time for recognition. (C) 1997 Elsevier Science B.V.