Face Recognition Under Varying Pose
While researchers in computer vision and pattern recognition have worked on automatic techniques for recognizing faces for the last 20 years, most systems specialize on frontal views of the face. We present a face recognizer that works under varying pose, the difficult part of which is to handle fac...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6621 |
| _version_ | 1826208382785159168 |
|---|---|
| author | Beymer, David J. |
| author_facet | Beymer, David J. |
| author_sort | Beymer, David J. |
| collection | MIT |
| description | While researchers in computer vision and pattern recognition have worked on automatic techniques for recognizing faces for the last 20 years, most systems specialize on frontal views of the face. We present a face recognizer that works under varying pose, the difficult part of which is to handle face rotations in depth. Building on successful template-based systems, our basic approach is to represent faces with templates from multiple model views that cover different poses from the viewing sphere. Our system has achieved a recognition rate of 98% on a data base of 62 people containing 10 testing and 15 modelling views per person. |
| first_indexed | 2024-09-23T14:04:33Z |
| id | mit-1721.1/6621 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:04:33Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/66212019-04-12T08:31:39Z Face Recognition Under Varying Pose Beymer, David J. While researchers in computer vision and pattern recognition have worked on automatic techniques for recognizing faces for the last 20 years, most systems specialize on frontal views of the face. We present a face recognizer that works under varying pose, the difficult part of which is to handle face rotations in depth. Building on successful template-based systems, our basic approach is to represent faces with templates from multiple model views that cover different poses from the viewing sphere. Our system has achieved a recognition rate of 98% on a data base of 62 people containing 10 testing and 15 modelling views per person. 2004-10-08T20:34:36Z 2004-10-08T20:34:36Z 1993-12-01 AIM-1461 http://hdl.handle.net/1721.1/6621 en_US AIM-1461 1032453 bytes 1152182 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | Beymer, David J. Face Recognition Under Varying Pose |
| title | Face Recognition Under Varying Pose |
| title_full | Face Recognition Under Varying Pose |
| title_fullStr | Face Recognition Under Varying Pose |
| title_full_unstemmed | Face Recognition Under Varying Pose |
| title_short | Face Recognition Under Varying Pose |
| title_sort | face recognition under varying pose |
| url | http://hdl.handle.net/1721.1/6621 |
| work_keys_str_mv | AT beymerdavidj facerecognitionundervaryingpose |