T. Jebara, M.D. Levine The detection, recognition and tracking of human faces in a cluttered background in real-time is being investigated. We propose a system which detects facial features from an edge map using a symmetry operator. The locations of key facial features are then used to normalize the facial image. The method, similar to Pentland's, first employs the Karhunen-Loeve expansion of the normalized facial image. The resulting linear combination of eigenvectors representing the data, forms a weight vector which is used to search for a matching face in a database. Normalization is achieved by using 3D models of human faces obtained using our rangefinders.