Accession Number : ADA290205

Title :   Face Recognition Under Varying Pose.

Descriptive Note : Memorandum rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Beymer, David J.

PDF Url : ADA290205

Report Date : DEC 1993

Pagination or Media Count : 15

Abstract : 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.

Descriptors :   *COMPUTER VISION, *FACE(ANATOMY), DATA BASES, MODELS, SPHERES, TEMPLATES, PATTERN RECOGNITION, AUTOMATIC, VIEWERS.

Subject Categories : Computer Programming and Software
      Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE