Fingerprint template protection using minutia-pair spectral representations

Taras Stanko, Bin Chen, Boris Škorić (Corresponding author)

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Uittreksel

Storage of biometric data requires some form of template protection in order to preserve the privacy of people enrolled in a biometric database. One approach is to use a Helper Data System. Here it is necessary to transform the raw biometric measurement into a fixed-length representation. In this paper, we extend the spectral function approach of Stanko and Škorić (IEEE Workshop on Information Forensics and Security (WIFS), 2017) which provides such a fixed-length representation for fingerprints. First, we introduce a new spectral function that captures different information from the minutia orientations. It is complementary to the original spectral function, and we use both of them to extract information from a fingerprint image. Second, we construct a helper data system consisting of zero-leakage quantisation followed by the Code Offset Method. We show empirical data on matching performance and entropy content. On the negative side, transforming a list of minutiae to the spectral representation degrades the matching performance significantly. On the positive side, adding privacy protection to the spectral representation can be done with little loss of performance.

TaalEngels
Artikelnummer12
Aantal pagina's15
TijdschriftEURASIP Journal on Information Security
Volume2019
Nummer van het tijdschrift1
DOI's
StatusGepubliceerd - 1 dec 2019

Vingerafdruk

Biometrics
Entropy

Trefwoorden

    Citeer dit

    @article{097ca13599d441c9a35c0a2004e5786c,
    title = "Fingerprint template protection using minutia-pair spectral representations",
    abstract = "Storage of biometric data requires some form of template protection in order to preserve the privacy of people enrolled in a biometric database. One approach is to use a Helper Data System. Here it is necessary to transform the raw biometric measurement into a fixed-length representation. In this paper, we extend the spectral function approach of Stanko and Škorić (IEEE Workshop on Information Forensics and Security (WIFS), 2017) which provides such a fixed-length representation for fingerprints. First, we introduce a new spectral function that captures different information from the minutia orientations. It is complementary to the original spectral function, and we use both of them to extract information from a fingerprint image. Second, we construct a helper data system consisting of zero-leakage quantisation followed by the Code Offset Method. We show empirical data on matching performance and entropy content. On the negative side, transforming a list of minutiae to the spectral representation degrades the matching performance significantly. On the positive side, adding privacy protection to the spectral representation can be done with little loss of performance.",
    keywords = "Fingerprint recognition, Helper data, Minutiae, Template protection",
    author = "Taras Stanko and Bin Chen and Boris Škorić",
    year = "2019",
    month = "12",
    day = "1",
    doi = "10.1186/s13635-019-0096-0",
    language = "English",
    volume = "2019",
    journal = "EURASIP Journal on Information Security",
    issn = "2510-523X",
    publisher = "Springer Open",
    number = "1",

    }

    Fingerprint template protection using minutia-pair spectral representations. / Stanko, Taras; Chen, Bin; Škorić, Boris (Corresponding author).

    In: EURASIP Journal on Information Security, Vol. 2019, Nr. 1, 12, 01.12.2019.

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    TY - JOUR

    T1 - Fingerprint template protection using minutia-pair spectral representations

    AU - Stanko,Taras

    AU - Chen,Bin

    AU - Škorić,Boris

    PY - 2019/12/1

    Y1 - 2019/12/1

    N2 - Storage of biometric data requires some form of template protection in order to preserve the privacy of people enrolled in a biometric database. One approach is to use a Helper Data System. Here it is necessary to transform the raw biometric measurement into a fixed-length representation. In this paper, we extend the spectral function approach of Stanko and Škorić (IEEE Workshop on Information Forensics and Security (WIFS), 2017) which provides such a fixed-length representation for fingerprints. First, we introduce a new spectral function that captures different information from the minutia orientations. It is complementary to the original spectral function, and we use both of them to extract information from a fingerprint image. Second, we construct a helper data system consisting of zero-leakage quantisation followed by the Code Offset Method. We show empirical data on matching performance and entropy content. On the negative side, transforming a list of minutiae to the spectral representation degrades the matching performance significantly. On the positive side, adding privacy protection to the spectral representation can be done with little loss of performance.

    AB - Storage of biometric data requires some form of template protection in order to preserve the privacy of people enrolled in a biometric database. One approach is to use a Helper Data System. Here it is necessary to transform the raw biometric measurement into a fixed-length representation. In this paper, we extend the spectral function approach of Stanko and Škorić (IEEE Workshop on Information Forensics and Security (WIFS), 2017) which provides such a fixed-length representation for fingerprints. First, we introduce a new spectral function that captures different information from the minutia orientations. It is complementary to the original spectral function, and we use both of them to extract information from a fingerprint image. Second, we construct a helper data system consisting of zero-leakage quantisation followed by the Code Offset Method. We show empirical data on matching performance and entropy content. On the negative side, transforming a list of minutiae to the spectral representation degrades the matching performance significantly. On the positive side, adding privacy protection to the spectral representation can be done with little loss of performance.

    KW - Fingerprint recognition

    KW - Helper data

    KW - Minutiae

    KW - Template protection

    UR - http://www.scopus.com/inward/record.url?scp=85071646876&partnerID=8YFLogxK

    U2 - 10.1186/s13635-019-0096-0

    DO - 10.1186/s13635-019-0096-0

    M3 - Article

    VL - 2019

    JO - EURASIP Journal on Information Security

    T2 - EURASIP Journal on Information Security

    JF - EURASIP Journal on Information Security

    SN - 2510-523X

    IS - 1

    M1 - 12

    ER -