Conditions for Viewpoint Dependent Face Recognition.

Abstract

Poggio and Vetter 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. (AN)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1993
Accession Number
ADA290098

Entities

People

  • Heinrich H. Buelthoff
  • Philippe G Schyns

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Age Groups
  • Artificial Intelligence
  • Computer Vision
  • False Alarms
  • Identification
  • Information Operations
  • Information Systems
  • Learning
  • Light Sources
  • Object Recognition
  • Reaction Time
  • Recognition
  • Rotation
  • Symmetry
  • Three Dimensional
  • Warning Systems

Fields of Study

  • Psychology

Readers

  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • Directed Energy