Abstract
Eigenvalue estimation plays an important role in biometrics. However, if the number of samples is limited, estimates are significantly biased. In this article we analyse the influence of this bias on the error rates of PCA/LDA based verification systems, using both synthetic data with realistic parameters and real biometric data. Results of bias correction in the verification systems differ considerable between synthetic data and real data: while the bias is responsible for a large part of classification errors in the synthetic facial data, compensation of the bias in real facial data leads only to marginal improvements.
Original language | English |
---|---|
Title of host publication | Advances in Biometrics |
Subtitle of host publication | Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings |
Place of Publication | Berlin / Heidelberg |
Publisher | Springer |
Pages | 189-198 |
Number of pages | 10 |
ISBN (Print) | 978-3-642-01792-6 |
DOIs | |
Publication status | Published - Jun 2009 |
Event | 3rd IAPR International Conference on Biometrics, ICB 2009 - University of Sassari, Alghero, Italy Duration: 2 Jun 2009 → 5 Jun 2009 Conference number: 3 |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer |
Volume | 5558 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Conference
Conference | 3rd IAPR International Conference on Biometrics, ICB 2009 |
---|---|
Abbreviated title | ICB |
Country/Territory | Italy |
City | Alghero |
Period | 2/06/09 → 5/06/09 |
Keywords
- METIS-263916
- Marcenko Pastur equation
- IR-67802
- EWI-15687
- Face Recognition
- SCS-Safety
- Eigenvalue correction