Conditions for Viewpoint Dependent Face Recognition
Citable URI:
http://hdl.handle.net/1721.1/7213
| Title: | Conditions for Viewpoint Dependent Face Recognition |
| Author: | Schyns, Philippe G.; Bulthoff, Heinrich H. |
| Issue Date: | 1993-08-01 |
| Abstract: | Poggio and Vetter (1992) showed that learning one view of a bilaterally symmetric object could be sufficient for its recognition, if this view allows the computation of a symmetric, "virtual," view. Faces are roughly bilaterally symmetric objects. Learning a side-view--which always has a symmetric view--should allow for better generalization performances than learning the frontal view. Two psychophysical experiments tested these predictions. Stimuli were views of shaded 3D models of laser-scanned faces. The first experiment tested whether a particular view of a face was canonical. The second experiment tested which single views of a face give rise to best generalization performances. The results were compatible with the symmetry hypothesis: Learning a side view allowed better generalization performances than learning the frontal view. |
| URI: | http://hdl.handle.net/1721.1/7213 |
| Other Identifiers: | AIM-1432 CBCL-081 |
| Series/Report no.: | AIM-1432, CBCL-081 |
| Keywords: | face recognition, RBF Network Symmetry |
Files in this item
| Files | Size | Format |
|---|---|---|
| AIM-1432.pdf | 746.3Kb | application/pdf |
| AIM-1432.ps.Z | 215.8Kb | application/octet-stream |
This item appears in the following Collection(s)
All Items in DSpace@MIT are protected by original copyright, with all rights reserved, unless otherwise indicated.
|
|
Contact
MIT Libraries
|