Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization

Meiru Mu, X. Shao, Qiuqi Ruan, Lieuwe Jan Spreeuwers, Raymond N.J. Veldhuis

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

    19 Downloads (Pure)

    Abstract

    In this paper, we propose a method of fixed-length binary string extraction (denoted by LogGM_DROBA) from low-resolution palmprint image for developing palmprint template protection technology. In order to extract reliable (stable and discriminative) bits, multi-bit equal-probability-interval quantization and detection rate optimized bit allocation (DROBA) are operated on the real-valued features, which are resulted from representing the palmprint image by simple statistics on logarithmic transform of Gabor magnitude (LogGM). Assuming the Helper Data Scheme with a BCH error correction coding is adopted for template protection, the performance is evaluated on the Hong Kong PolyU palmprint database. The experimental results show that our method can achieve low Bit Error Rate (BER) resulted from genuine binary strings so that a long secret key (around 100 bits) is allowed to be combined for security, and low False Rejection Rate and low False Acceptance Rate (FRR/FAR) when the key retrial process is considered as a Hamming distance classifier, which verify the high stability and strong distinctive ability of our extracted palmprint binary string.
    Original languageUndefined
    Title of host publicationProceedings of the 2013 International Conference on Biometrics (ICB)
    Place of PublicationPiscataway, NJ, USA
    PublisherIEEE
    Pages1-7
    Number of pages7
    ISBN (Print)978-1-4799-0310-8
    DOIs
    Publication statusPublished - 4 Jun 2013
    Event6th IAPR International Conference on Biometrics, ICB 2013 - School of Mining Engineering, Madrid, Spain
    Duration: 4 Jun 20137 Jun 2013
    Conference number: 6
    https://atvs.ii.uam.es/icb2013/

    Publication series

    Name
    PublisherIEEE

    Conference

    Conference6th IAPR International Conference on Biometrics, ICB 2013
    Abbreviated titleICB
    CountrySpain
    CityMadrid
    Period4/06/137/06/13
    Internet address

    Keywords

    • EWI-23947
    • SCS-Safety
    • Palmprint
    • IR-87791
    • Template Protection
    • Biometrics
    • METIS-300147
    • gabor filter

    Cite this

    Mu, M., Shao, X., Ruan, Q., Spreeuwers, L. J., & Veldhuis, R. N. J. (2013). Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization. In Proceedings of the 2013 International Conference on Biometrics (ICB) (pp. 1-7). Piscataway, NJ, USA: IEEE. https://doi.org/10.1109/ICB.2013.6612998
    Mu, Meiru ; Shao, X. ; Ruan, Qiuqi ; Spreeuwers, Lieuwe Jan ; Veldhuis, Raymond N.J. / Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization. Proceedings of the 2013 International Conference on Biometrics (ICB). Piscataway, NJ, USA : IEEE, 2013. pp. 1-7
    @inproceedings{63c6d44f16404f169652aa77c154cd3e,
    title = "Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization",
    abstract = "In this paper, we propose a method of fixed-length binary string extraction (denoted by LogGM_DROBA) from low-resolution palmprint image for developing palmprint template protection technology. In order to extract reliable (stable and discriminative) bits, multi-bit equal-probability-interval quantization and detection rate optimized bit allocation (DROBA) are operated on the real-valued features, which are resulted from representing the palmprint image by simple statistics on logarithmic transform of Gabor magnitude (LogGM). Assuming the Helper Data Scheme with a BCH error correction coding is adopted for template protection, the performance is evaluated on the Hong Kong PolyU palmprint database. The experimental results show that our method can achieve low Bit Error Rate (BER) resulted from genuine binary strings so that a long secret key (around 100 bits) is allowed to be combined for security, and low False Rejection Rate and low False Acceptance Rate (FRR/FAR) when the key retrial process is considered as a Hamming distance classifier, which verify the high stability and strong distinctive ability of our extracted palmprint binary string.",
    keywords = "EWI-23947, SCS-Safety, Palmprint, IR-87791, Template Protection, Biometrics, METIS-300147, gabor filter",
    author = "Meiru Mu and X. Shao and Qiuqi Ruan and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.}",
    note = "eemcs-eprint-23947",
    year = "2013",
    month = "6",
    day = "4",
    doi = "10.1109/ICB.2013.6612998",
    language = "Undefined",
    isbn = "978-1-4799-0310-8",
    publisher = "IEEE",
    pages = "1--7",
    booktitle = "Proceedings of the 2013 International Conference on Biometrics (ICB)",
    address = "United States",

    }

    Mu, M, Shao, X, Ruan, Q, Spreeuwers, LJ & Veldhuis, RNJ 2013, Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization. in Proceedings of the 2013 International Conference on Biometrics (ICB). IEEE, Piscataway, NJ, USA, pp. 1-7, 6th IAPR International Conference on Biometrics, ICB 2013, Madrid, Spain, 4/06/13. https://doi.org/10.1109/ICB.2013.6612998

    Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization. / Mu, Meiru; Shao, X.; Ruan, Qiuqi; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

    Proceedings of the 2013 International Conference on Biometrics (ICB). Piscataway, NJ, USA : IEEE, 2013. p. 1-7.

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

    TY - GEN

    T1 - Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization

    AU - Mu, Meiru

    AU - Shao, X.

    AU - Ruan, Qiuqi

    AU - Spreeuwers, Lieuwe Jan

    AU - Veldhuis, Raymond N.J.

    N1 - eemcs-eprint-23947

    PY - 2013/6/4

    Y1 - 2013/6/4

    N2 - In this paper, we propose a method of fixed-length binary string extraction (denoted by LogGM_DROBA) from low-resolution palmprint image for developing palmprint template protection technology. In order to extract reliable (stable and discriminative) bits, multi-bit equal-probability-interval quantization and detection rate optimized bit allocation (DROBA) are operated on the real-valued features, which are resulted from representing the palmprint image by simple statistics on logarithmic transform of Gabor magnitude (LogGM). Assuming the Helper Data Scheme with a BCH error correction coding is adopted for template protection, the performance is evaluated on the Hong Kong PolyU palmprint database. The experimental results show that our method can achieve low Bit Error Rate (BER) resulted from genuine binary strings so that a long secret key (around 100 bits) is allowed to be combined for security, and low False Rejection Rate and low False Acceptance Rate (FRR/FAR) when the key retrial process is considered as a Hamming distance classifier, which verify the high stability and strong distinctive ability of our extracted palmprint binary string.

    AB - In this paper, we propose a method of fixed-length binary string extraction (denoted by LogGM_DROBA) from low-resolution palmprint image for developing palmprint template protection technology. In order to extract reliable (stable and discriminative) bits, multi-bit equal-probability-interval quantization and detection rate optimized bit allocation (DROBA) are operated on the real-valued features, which are resulted from representing the palmprint image by simple statistics on logarithmic transform of Gabor magnitude (LogGM). Assuming the Helper Data Scheme with a BCH error correction coding is adopted for template protection, the performance is evaluated on the Hong Kong PolyU palmprint database. The experimental results show that our method can achieve low Bit Error Rate (BER) resulted from genuine binary strings so that a long secret key (around 100 bits) is allowed to be combined for security, and low False Rejection Rate and low False Acceptance Rate (FRR/FAR) when the key retrial process is considered as a Hamming distance classifier, which verify the high stability and strong distinctive ability of our extracted palmprint binary string.

    KW - EWI-23947

    KW - SCS-Safety

    KW - Palmprint

    KW - IR-87791

    KW - Template Protection

    KW - Biometrics

    KW - METIS-300147

    KW - gabor filter

    U2 - 10.1109/ICB.2013.6612998

    DO - 10.1109/ICB.2013.6612998

    M3 - Conference contribution

    SN - 978-1-4799-0310-8

    SP - 1

    EP - 7

    BT - Proceedings of the 2013 International Conference on Biometrics (ICB)

    PB - IEEE

    CY - Piscataway, NJ, USA

    ER -

    Mu M, Shao X, Ruan Q, Spreeuwers LJ, Veldhuis RNJ. Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization. In Proceedings of the 2013 International Conference on Biometrics (ICB). Piscataway, NJ, USA: IEEE. 2013. p. 1-7 https://doi.org/10.1109/ICB.2013.6612998