Fuzzy Normalisation Methods for Pattern Verification

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract

    A fuzzy approach to normalisation methods for pattern verification is presented in this paper. For an input token and a claimed identity, a score is calculated and compared with a given threshold to accept or reject the claimed person. The score is regarded as a fuzzy memebership function in this approach. The paper shows how to find effective scores to reduce both false rejection and false acceptance errors. Speaker verification experiments performed on the ANDOSL database and utterance verification experiments performed on the TI46 database showed better results for fuzzy methods
    Original languageEnglish
    Title of host publicationInternational Conference on Biometric Authentication, ICBA 2004
    EditorsD Zhang, AK Jain
    Place of PublicationBerlin Heidelberg, Germany.
    PublisherSpringer
    Pages648-654
    Number of pages7
    ISBN (Print)9783540221463
    DOIs
    Publication statusPublished - 2004
    EventInternational Conference on Biometric Authentication - , Hong Kong
    Duration: 15 Jul 200417 Jul 2004

    Conference

    ConferenceInternational Conference on Biometric Authentication
    CountryHong Kong
    Period15/07/0417/07/04

    Fingerprint

    Experiments

    Cite this

    Tran, D. (2004). Fuzzy Normalisation Methods for Pattern Verification. In D. Zhang, & AK. Jain (Eds.), International Conference on Biometric Authentication, ICBA 2004 (pp. 648-654). Berlin Heidelberg, Germany.: Springer. https://doi.org/10.1007/978-3-540-25948-0_88
    Tran, Dat. / Fuzzy Normalisation Methods for Pattern Verification. International Conference on Biometric Authentication, ICBA 2004. editor / D Zhang ; AK Jain. Berlin Heidelberg, Germany. : Springer, 2004. pp. 648-654
    @inproceedings{1c3773d1aedc4af7a79967d41c759991,
    title = "Fuzzy Normalisation Methods for Pattern Verification",
    abstract = "A fuzzy approach to normalisation methods for pattern verification is presented in this paper. For an input token and a claimed identity, a score is calculated and compared with a given threshold to accept or reject the claimed person. The score is regarded as a fuzzy memebership function in this approach. The paper shows how to find effective scores to reduce both false rejection and false acceptance errors. Speaker verification experiments performed on the ANDOSL database and utterance verification experiments performed on the TI46 database showed better results for fuzzy methods",
    author = "Dat Tran",
    year = "2004",
    doi = "10.1007/978-3-540-25948-0_88",
    language = "English",
    isbn = "9783540221463",
    pages = "648--654",
    editor = "D Zhang and AK Jain",
    booktitle = "International Conference on Biometric Authentication, ICBA 2004",
    publisher = "Springer",
    address = "Netherlands",

    }

    Tran, D 2004, Fuzzy Normalisation Methods for Pattern Verification. in D Zhang & AK Jain (eds), International Conference on Biometric Authentication, ICBA 2004. Springer, Berlin Heidelberg, Germany., pp. 648-654, International Conference on Biometric Authentication, Hong Kong, 15/07/04. https://doi.org/10.1007/978-3-540-25948-0_88

    Fuzzy Normalisation Methods for Pattern Verification. / Tran, Dat.

    International Conference on Biometric Authentication, ICBA 2004. ed. / D Zhang; AK Jain. Berlin Heidelberg, Germany. : Springer, 2004. p. 648-654.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Fuzzy Normalisation Methods for Pattern Verification

    AU - Tran, Dat

    PY - 2004

    Y1 - 2004

    N2 - A fuzzy approach to normalisation methods for pattern verification is presented in this paper. For an input token and a claimed identity, a score is calculated and compared with a given threshold to accept or reject the claimed person. The score is regarded as a fuzzy memebership function in this approach. The paper shows how to find effective scores to reduce both false rejection and false acceptance errors. Speaker verification experiments performed on the ANDOSL database and utterance verification experiments performed on the TI46 database showed better results for fuzzy methods

    AB - A fuzzy approach to normalisation methods for pattern verification is presented in this paper. For an input token and a claimed identity, a score is calculated and compared with a given threshold to accept or reject the claimed person. The score is regarded as a fuzzy memebership function in this approach. The paper shows how to find effective scores to reduce both false rejection and false acceptance errors. Speaker verification experiments performed on the ANDOSL database and utterance verification experiments performed on the TI46 database showed better results for fuzzy methods

    U2 - 10.1007/978-3-540-25948-0_88

    DO - 10.1007/978-3-540-25948-0_88

    M3 - Conference contribution

    SN - 9783540221463

    SP - 648

    EP - 654

    BT - International Conference on Biometric Authentication, ICBA 2004

    A2 - Zhang, D

    A2 - Jain, AK

    PB - Springer

    CY - Berlin Heidelberg, Germany.

    ER -

    Tran D. Fuzzy Normalisation Methods for Pattern Verification. In Zhang D, Jain AK, editors, International Conference on Biometric Authentication, ICBA 2004. Berlin Heidelberg, Germany.: Springer. 2004. p. 648-654 https://doi.org/10.1007/978-3-540-25948-0_88