Advanced Search

Pose-Invariant Face Recognition Using Real and Virtual Views

Research and Teaching Output of the MIT Community

Show simple item record Beymer, David en_US 2004-10-20T14:45:14Z 2004-10-20T14:45:14Z 1996-03-28 en_US
dc.identifier.other AITR-1574 en_US
dc.description.abstract The problem of automatic face recognition is to visually identify a person in an input image. This task is performed by matching the input face against the faces of known people in a database of faces. Most existing work in face recognition has limited the scope of the problem, however, by dealing primarily with frontal views, neutral expressions, and fixed lighting conditions. To help generalize existing face recognition systems, we look at the problem of recognizing faces under a range of viewpoints. In particular, we consider two cases of this problem: (i) many example views are available of each person, and (ii) only one view is available per person, perhaps a driver's license or passport photograph. Ideally, we would like to address these two cases using a simple view-based approach, where a person is represented in the database by using a number of views on the viewing sphere. While the view-based approach is consistent with case (i), for case (ii) we need to augment the single real view of each person with synthetic views from other viewpoints, views we call 'virtual views'. Virtual views are generated using prior knowledge of face rotation, knowledge that is 'learned' from images of prototype faces. This prior knowledge is used to effectively rotate in depth the single real view available of each person. In this thesis, I present the view-based face recognizer, techniques for synthesizing virtual views, and experimental results using real and virtual views in the recognizer. en_US
dc.format.extent 184 p. en_US
dc.format.extent 26649678 bytes
dc.format.extent 5871601 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AITR-1574 en_US
dc.subject AI en_US
dc.subject MIT en_US
dc.subject Artificial Intelligence en_US
dc.subject computer vision en_US
dc.subject sface recognition en_US
dc.subject facial feature detection en_US
dc.subject virtualsviews en_US
dc.title Pose-Invariant Face Recognition Using Real and Virtual Views en_US

Files in this item

Name Size Format Description 25.41Mb Postscript
AITR-1574.pdf 5.599Mb PDF

This item appears in the following Collection(s)

Show simple item record