Analysis of eigenvalue correction applied to biometrics

Anne Hendrikse, Raymond Veldhuis, Luuk Spreeuwers, Asker Bazen

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    3 Citations (Scopus)
    41 Downloads (Pure)

    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 languageEnglish
    Title of host publicationAdvances in Biometrics
    Subtitle of host publicationThird International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings
    Place of PublicationBerlin / Heidelberg
    PublisherSpringer
    Pages189-198
    Number of pages10
    ISBN (Print)978-3-642-01792-6
    DOIs
    Publication statusPublished - Jun 2009
    Event3rd IAPR International Conference on Biometrics, ICB 2009 - University of Sassari, Alghero, Italy
    Duration: 2 Jun 20095 Jun 2009
    Conference number: 3

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume5558
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    Conference3rd IAPR International Conference on Biometrics, ICB 2009
    Abbreviated titleICB
    CountryItaly
    CityAlghero
    Period2/06/095/06/09

    Fingerprint

    biometry
    eigenvalue
    analysis

    Keywords

    • METIS-263916
    • Marcenko Pastur equation
    • IR-67802
    • EWI-15687
    • Face Recognition
    • SCS-Safety
    • Eigenvalue correction

    Cite this

    Hendrikse, A., Veldhuis, R., Spreeuwers, L., & Bazen, A. (2009). Analysis of eigenvalue correction applied to biometrics. In Advances in Biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings (pp. 189-198). (Lecture Notes in Computer Science; Vol. 5558). Berlin / Heidelberg: Springer. https://doi.org/10.1007/978-3-642-01793-3_20
    Hendrikse, Anne ; Veldhuis, Raymond ; Spreeuwers, Luuk ; Bazen, Asker. / Analysis of eigenvalue correction applied to biometrics. Advances in Biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. Berlin / Heidelberg : Springer, 2009. pp. 189-198 (Lecture Notes in Computer Science).
    @inproceedings{92e2e9e4a8ca4cb481bd5e839568cd97,
    title = "Analysis of eigenvalue correction applied to biometrics",
    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.",
    keywords = "METIS-263916, Marcenko Pastur equation, IR-67802, EWI-15687, Face Recognition, SCS-Safety, Eigenvalue correction",
    author = "Anne Hendrikse and Raymond Veldhuis and Luuk Spreeuwers and Asker Bazen",
    note = "10.1007/978-3-642-01793-3_20",
    year = "2009",
    month = "6",
    doi = "10.1007/978-3-642-01793-3_20",
    language = "English",
    isbn = "978-3-642-01792-6",
    series = "Lecture Notes in Computer Science",
    publisher = "Springer",
    pages = "189--198",
    booktitle = "Advances in Biometrics",

    }

    Hendrikse, A, Veldhuis, R, Spreeuwers, L & Bazen, A 2009, Analysis of eigenvalue correction applied to biometrics. in Advances in Biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. Lecture Notes in Computer Science, vol. 5558, Springer, Berlin / Heidelberg, pp. 189-198, 3rd IAPR International Conference on Biometrics, ICB 2009, Alghero, Italy, 2/06/09. https://doi.org/10.1007/978-3-642-01793-3_20

    Analysis of eigenvalue correction applied to biometrics. / Hendrikse, Anne; Veldhuis, Raymond; Spreeuwers, Luuk; Bazen, Asker.

    Advances in Biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. Berlin / Heidelberg : Springer, 2009. p. 189-198 (Lecture Notes in Computer Science; Vol. 5558).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Analysis of eigenvalue correction applied to biometrics

    AU - Hendrikse, Anne

    AU - Veldhuis, Raymond

    AU - Spreeuwers, Luuk

    AU - Bazen, Asker

    N1 - 10.1007/978-3-642-01793-3_20

    PY - 2009/6

    Y1 - 2009/6

    N2 - 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.

    AB - 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.

    KW - METIS-263916

    KW - Marcenko Pastur equation

    KW - IR-67802

    KW - EWI-15687

    KW - Face Recognition

    KW - SCS-Safety

    KW - Eigenvalue correction

    U2 - 10.1007/978-3-642-01793-3_20

    DO - 10.1007/978-3-642-01793-3_20

    M3 - Conference contribution

    SN - 978-3-642-01792-6

    T3 - Lecture Notes in Computer Science

    SP - 189

    EP - 198

    BT - Advances in Biometrics

    PB - Springer

    CY - Berlin / Heidelberg

    ER -

    Hendrikse A, Veldhuis R, Spreeuwers L, Bazen A. Analysis of eigenvalue correction applied to biometrics. In Advances in Biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. Berlin / Heidelberg: Springer. 2009. p. 189-198. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-01793-3_20