Face Analysis

Computer Analysis of Images and Patterns

Volume 1296 of the series Lecture Notes in Computer Science pp 456-463

Date:

Face recognition by elastic bunch graph matching

  • Laurenz WiskottAffiliated withInstitut für Neuroinformatik, Ruhr-Universität Bochum Email author 
  • , Jean-Marc FellousAffiliated withComputer Science Department, University of Southern California
  • , Norbert KrügerAffiliated withInstitut für Neuroinformatik, Ruhr-Universität Bochum
  • , Christoph von der MalsburgAffiliated withInstitut für Neuroinformatik, Ruhr-Universität BochumComputer Science Department, University of Southern California

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We present a system for recognizing human faces from single images out of a large database with one image per person. The task is difficult because of image variation in terms of position, size, expression, and pose. The system collapses most of this variance by extracting concise face descriptions in the form of image graphs. In these, fiducial points on the face (eyes, mouth etc.) are described by sets of wavelet components (jets). Image graph extraction is based on a novel approach, the bunch graph, which is constructed from a small set of sample image graphs. Recognition is based on a straight-forward comparison of image graphs. We report recognition experiments on the FERET database and the Bochum database, including recognition across pose.