Accession Number : ADA290098

Title :   Conditions for Viewpoint Dependent Face Recognition.

Descriptive Note : Memo rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Schyns, Philippe G. ; Buelthoff, Heinrich H.

PDF Url : ADA290098

Report Date : AUG 1993

Pagination or Media Count : 7

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)

Descriptors :   *IMAGE PROCESSING, *PATTERN RECOGNITION, *PSYCHOPHYSICS, STIMULATION(PHYSIOLOGY), EXPERIMENTAL DATA, PERFORMANCE(HUMAN), COGNITION, TARGET DISCRIMINATION, THREE DIMENSIONAL, SYMMETRY, COMPUTER VISION, VISUAL PERCEPTION, LEARNING, NEUROPHYSIOLOGY.

Subject Categories : Psychology
      Anatomy and Physiology
      Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE