Photometric normalisation for face verification

  • Authors:
  • James Short;Josef Kittler;Kieron Messer

  • Affiliations:
  • Centre for Vision, Speech and Signal Processing, University of Surrey, UK;Centre for Vision, Speech and Signal Processing, University of Surrey, UK;Centre for Vision, Speech and Signal Processing, University of Surrey, UK

  • Venue:
  • AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Further to previous work showing the superiority of the pre-processing algorithm developed by Gross and Brajovic, we propose improvements that remove the need for parameter selection. In extensive experimentation on the XM2VTS database, the Yale B database and the BANCA database, we show that our method of automatic parameter selection can produce better results than setting the parameter to a single value for the whole database.