Biometrie authentication platform-based multisensor fusion

摘要

The system proposed in this paper is an innovative biometrie authentication platform for access control applications based face recognition. The vision system is based multisensor fusion combining catadioptric sensor (calibrated with a field of view of 360°) and a Pan Tilt Zoom camera (PTZ). It is able to detect and track moving objects with a high zoom level. The recognition process is based on detection of the moving person and detection of a region of interest representing the face. Face Recognition is based on the modified Eigenface algorithm. The entire development was validated using an heterogeneous database combining ORL database (Olivetti Research Laboratories) and our own Nomad Biometric Authentication database.