Independent component analysis for face authentication

Havran, Carmen;Hupet, Laurent;Czyz, Jacek;Lee, John;Verleysen, Michel;et.al.
(2002) International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES 2002) — Location: Crema (Italy) (16.September.2002)

Files

C15-IndependentComponentAnalysisforfaceauthentication.pdf
  • Restricted Access
  • Adobe PDF
  • 53.7 KB
Request a copy

Details

Authors
Show more
Abstract
Independent component analysis (ICA) is presented as an alternative feature extraction algorithm to principal component analysis (PCA) widely used in automatic face recognition/authentication tasks. We show that the promising ICA algorithm extracts from faces features that are relevant and efficient for authentication. This leads to improved success rates and a reduced client model size over a PCA based feature extraction.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Havran, C., Hupet, L., Czyz, J., Lee, J., Vandendorpe, L., & Verleysen, M. (2002). Independent component analysis for face authentication. In Damiani, E.; Howlett, R.J.; Jain, L.C.; Ichalkaranje, N. (ed.), Knowledge-Based Intelligent Information Engineering Systems and Allied Technologies (pp. 1207-1211). IOS press. https://hdl.handle.net/2078.5/253971