Face Recognition from One Example View

To create a pose-invariant face recognizer, one strategy is the view-based approach, which uses a set of example views at di erent poses. But what if we only have one example view available, such as a scanned passport photo { can we still recognize faces under di erent poses? Given one example view at a known pose, it is still possible to use the view-based approach by exploiting prior knowledge of faces to generate virtual views, or views of the face as seen from di erent poses. To represent prior knowledge, we use 2D example views of prototype faces under di erent rotations. We will develop example-based techniques for applying the rotation seen in the prototypes to essentially \rotate" the single real view which is available. Next, the combined set of one real and multiple virtual views is used as example views in a view-based, pose-invariant face recognizer. Our experiments suggest that for expressing prior knowledge of faces, 2D example-based approaches should be considered alongside the more standard 3D modeling techniques. Copyright c Massachusetts Institute of Technology, 1995 This report describes research done at the Arti cial Intelligence Laboratory and within the Center for Biological and Computational Learning. This research is sponsored by grants from the O ce of Naval Research under contracts N00014-91-J-1270 and N00014-92-J-1879; by a grant from the National Science Foundation under contract ASC-9217041. Support for the A.I. Laboratory's arti cial intelligence research is provided by ONR contract N00014-91-J-4038. D. Beymer is supported by a Howard Hughes Doctoral Fellowship from the Hughes Aircraft Company.