Two-step calibration method for multi-algorithm score-based face recognition systems by minimizing discrimination loss

Open Access
Authors
Publication date 2016
Host editors
  • J. Fierrez
  • S.Z. Li
  • A. Ross
  • R. Veldhuis
  • F. Alonso-Fernandez
  • J. Bigun
Book title 2016 International Conference on Biometrics (ICB)
Book subtitle proceedings : 13-16 June 2016. Halmstad, Sweden
ISBN
  • 9781509018703
ISBN (electronic)
  • 9781509018697
  • 9781509018680
Event 2016 International Conference on Biometrics (ICB)
Number of pages 7
Publisher Piscataway, NJ: IEEE
Organisations
  • Faculty of Science (FNWI) - Korteweg-de Vries Institute for Mathematics (KdVI)
  • Faculty of Science (FNWI)
Abstract We propose a new method for combining multi-algorithm score-based face recognition systems, which we call the two-step calibration method. Typically, algorithms for face recognition systems produce dependent scores. The two-step method is based on parametric copulas to handle this dependence. Its goal is to minimize discrimination loss. For synthetic and real databases (NIST-face and Face3D) we will show that our method is accurate and reliable using the cost of log likelihood ratio and the information-theoretical empirical cross-entropy (ECE).
Document type Conference contribution
Language English
Published at https://doi.org/10.1109/ICB.2016.7550094
Downloads
Two-step calibration method (Final published version)
Permalink to this page
Back