Return to search

Conditions for Viewpoint Dependent Face Recognition

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.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7213
Date01 August 1993
CreatorsSchyns, Philippe G., Bulthoff, Heinrich H.
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format6 p., 215801 bytes, 746385 bytes, application/octet-stream, application/pdf
RelationAIM-1432, CBCL-081

Page generated in 0.0019 seconds