Fingerprint Matching by Thin-plate Spline Modelling of Elastic Deformations

A.M. Bazen, Sabih H. Gerez

    Research output: Contribution to journalArticleAcademicpeer-review

    141 Citations (Scopus)
    210 Downloads (Pure)

    Abstract

    This paper presents a novel minutiae matching method that describes elastic distortions in fingerprints by means of a thin-plate spline model, which is estimated using a local and a global matching stage. After registration of the fingerprints according to the estimated model, the number of matching minutiae can be counted using very tight matching thresholds. For deformed fingerprints, the algorithm gives considerably higher matching scores compared to rigid matching algorithms, while only taking 100 ms on a 1 GHz P-III machine. Furthermore, it is shown that the observed deformations are different from those described by theoretical models proposed in the literature.
    Original languageUndefined
    Pages (from-to)1859-1867
    Number of pages9
    JournalPattern recognition
    Volume36
    Issue number8
    DOIs
    Publication statusPublished - 2003

    Keywords

    • Thin-plate spline models
    • Registration
    • IR-74906
    • Fingerprint verification
    • Elastic deformations
    • Minutiae matching
    • EWI-13309
    • SCS-Safety
    • METIS-216642

    Cite this

    @article{7ee9367ea9854a5ca75d2ddb5a3d8dfb,
    title = "Fingerprint Matching by Thin-plate Spline Modelling of Elastic Deformations",
    abstract = "This paper presents a novel minutiae matching method that describes elastic distortions in fingerprints by means of a thin-plate spline model, which is estimated using a local and a global matching stage. After registration of the fingerprints according to the estimated model, the number of matching minutiae can be counted using very tight matching thresholds. For deformed fingerprints, the algorithm gives considerably higher matching scores compared to rigid matching algorithms, while only taking 100 ms on a 1 GHz P-III machine. Furthermore, it is shown that the observed deformations are different from those described by theoretical models proposed in the literature.",
    keywords = "Thin-plate spline models, Registration, IR-74906, Fingerprint verification, Elastic deformations, Minutiae matching, EWI-13309, SCS-Safety, METIS-216642",
    author = "A.M. Bazen and Gerez, {Sabih H.}",
    note = "SAS 03-061",
    year = "2003",
    doi = "10.1016/S0031-3203(03)00036-0",
    language = "Undefined",
    volume = "36",
    pages = "1859--1867",
    journal = "Pattern recognition",
    issn = "0031-3203",
    publisher = "Elsevier",
    number = "8",

    }

    Fingerprint Matching by Thin-plate Spline Modelling of Elastic Deformations. / Bazen, A.M.; Gerez, Sabih H.

    In: Pattern recognition, Vol. 36, No. 8, 2003, p. 1859-1867.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Fingerprint Matching by Thin-plate Spline Modelling of Elastic Deformations

    AU - Bazen, A.M.

    AU - Gerez, Sabih H.

    N1 - SAS 03-061

    PY - 2003

    Y1 - 2003

    N2 - This paper presents a novel minutiae matching method that describes elastic distortions in fingerprints by means of a thin-plate spline model, which is estimated using a local and a global matching stage. After registration of the fingerprints according to the estimated model, the number of matching minutiae can be counted using very tight matching thresholds. For deformed fingerprints, the algorithm gives considerably higher matching scores compared to rigid matching algorithms, while only taking 100 ms on a 1 GHz P-III machine. Furthermore, it is shown that the observed deformations are different from those described by theoretical models proposed in the literature.

    AB - This paper presents a novel minutiae matching method that describes elastic distortions in fingerprints by means of a thin-plate spline model, which is estimated using a local and a global matching stage. After registration of the fingerprints according to the estimated model, the number of matching minutiae can be counted using very tight matching thresholds. For deformed fingerprints, the algorithm gives considerably higher matching scores compared to rigid matching algorithms, while only taking 100 ms on a 1 GHz P-III machine. Furthermore, it is shown that the observed deformations are different from those described by theoretical models proposed in the literature.

    KW - Thin-plate spline models

    KW - Registration

    KW - IR-74906

    KW - Fingerprint verification

    KW - Elastic deformations

    KW - Minutiae matching

    KW - EWI-13309

    KW - SCS-Safety

    KW - METIS-216642

    U2 - 10.1016/S0031-3203(03)00036-0

    DO - 10.1016/S0031-3203(03)00036-0

    M3 - Article

    VL - 36

    SP - 1859

    EP - 1867

    JO - Pattern recognition

    JF - Pattern recognition

    SN - 0031-3203

    IS - 8

    ER -