Partial fingerprint identification through correlation-based approach

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

    Abstract

    Partial fingerprints are likely to be fragmentary or low quality, which mandates the development of accurate fingerprint verification algorithms. Two fingerprints should be aligned properly, in order to measure the similarity between them. Moreover, the common fingerprint recognition methods (minutiae-based) only use the limited information that is available. This affects the reliability of the output of the fingerprint recognition system, especially when dealing with partial fingerprints. To overcome this drawback, in this research, a region-based fingerprint recognition method is proposed in which the fingerprints are compared in a pixel-wise manner by computing their correlation coefficient. Therefore, all the attributes of the fingerprint contribute in the matching decision. Such a technique is promising to accurately recognise a partial fingerprint as well as a full fingerprint compared to the minutiae-based fingerprint recognition methods which only concentrate
    on parts of the fingerprint. The proposed method is based on simple but effective metrics that has been de-fined to compute local similarities which is then combined into a global score and then used to make the match/non-match decision. Extensive experiments over FVC2002 data set has proven the superiority of our method compared to the other well-known techniques reported in literature.
    Original languageEnglish
    Title of host publicationProceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014)
    EditorsMohammad S Obaidat, Andreas Holzinger, Pierangela Samarati
    Place of PublicationSciTePress Digital Library
    PublisherScitepress
    Pages275 - 284
    Number of pages10
    ISBN (Print)9789897580451
    DOIs
    Publication statusPublished - 2014
    EventInternational Conference on Information Security and Cryptography 2014 - Vienna, Austria
    Duration: 28 Aug 201430 Aug 2014
    Conference number: 11th
    http://www.secrypt.icete.org/?y=2014

    Conference

    ConferenceInternational Conference on Information Security and Cryptography 2014
    Abbreviated titleSECRYPT 2014
    CountryAustria
    CityVienna
    Period28/08/1430/08/14
    OtherSECRYPT is part of ICETE, the 11th International Joint Conference on e-Business and Telecommunications.
    Registration to SECRYPT allows free access to all other ICETE conferences.

    ICETE 2014 will be held in conjunction with ICSOFT 2014, SIMULTECH 2014 and DATA 2014.
    Registration to ICETE allows free access to the ICSOFT, SIMULTECH and DATA conferences (as a non-speaker).
    Internet address

    Keywords

    • Biometric
    • Partial fingerprint
    • Identification
    • Authentication
    • Local correlation matching technique

    Cite this

    Zanganeh, O., Bhattacharjee, N., & Srinivasan, B. (2014). Partial fingerprint identification through correlation-based approach. In M. S. Obaidat, A. Holzinger, & P. Samarati (Eds.), Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014) (pp. 275 - 284). SciTePress Digital Library: Scitepress. https://doi.org/10.5220/0005045302750284
    Zanganeh, Omid ; Bhattacharjee, Nandita ; Srinivasan, Bala. / Partial fingerprint identification through correlation-based approach. Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014). editor / Mohammad S Obaidat ; Andreas Holzinger ; Pierangela Samarati. SciTePress Digital Library : Scitepress, 2014. pp. 275 - 284
    @inproceedings{2a47a927ae3b4e66bca4c98b926ab142,
    title = "Partial fingerprint identification through correlation-based approach",
    abstract = "Partial fingerprints are likely to be fragmentary or low quality, which mandates the development of accurate fingerprint verification algorithms. Two fingerprints should be aligned properly, in order to measure the similarity between them. Moreover, the common fingerprint recognition methods (minutiae-based) only use the limited information that is available. This affects the reliability of the output of the fingerprint recognition system, especially when dealing with partial fingerprints. To overcome this drawback, in this research, a region-based fingerprint recognition method is proposed in which the fingerprints are compared in a pixel-wise manner by computing their correlation coefficient. Therefore, all the attributes of the fingerprint contribute in the matching decision. Such a technique is promising to accurately recognise a partial fingerprint as well as a full fingerprint compared to the minutiae-based fingerprint recognition methods which only concentrateon parts of the fingerprint. The proposed method is based on simple but effective metrics that has been de-fined to compute local similarities which is then combined into a global score and then used to make the match/non-match decision. Extensive experiments over FVC2002 data set has proven the superiority of our method compared to the other well-known techniques reported in literature.",
    keywords = "Biometric, Partial fingerprint, Identification, Authentication, Local correlation matching technique",
    author = "Omid Zanganeh and Nandita Bhattacharjee and Bala Srinivasan",
    year = "2014",
    doi = "10.5220/0005045302750284",
    language = "English",
    isbn = "9789897580451",
    pages = "275 -- 284",
    editor = "Obaidat, {Mohammad S} and Andreas Holzinger and Pierangela Samarati",
    booktitle = "Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014)",
    publisher = "Scitepress",

    }

    Zanganeh, O, Bhattacharjee, N & Srinivasan, B 2014, Partial fingerprint identification through correlation-based approach. in MS Obaidat, A Holzinger & P Samarati (eds), Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014). Scitepress, SciTePress Digital Library, pp. 275 - 284, International Conference on Information Security and Cryptography 2014, Vienna, Austria, 28/08/14. https://doi.org/10.5220/0005045302750284

    Partial fingerprint identification through correlation-based approach. / Zanganeh, Omid; Bhattacharjee, Nandita; Srinivasan, Bala.

    Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014). ed. / Mohammad S Obaidat; Andreas Holzinger; Pierangela Samarati. SciTePress Digital Library : Scitepress, 2014. p. 275 - 284.

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

    TY - GEN

    T1 - Partial fingerprint identification through correlation-based approach

    AU - Zanganeh, Omid

    AU - Bhattacharjee, Nandita

    AU - Srinivasan, Bala

    PY - 2014

    Y1 - 2014

    N2 - Partial fingerprints are likely to be fragmentary or low quality, which mandates the development of accurate fingerprint verification algorithms. Two fingerprints should be aligned properly, in order to measure the similarity between them. Moreover, the common fingerprint recognition methods (minutiae-based) only use the limited information that is available. This affects the reliability of the output of the fingerprint recognition system, especially when dealing with partial fingerprints. To overcome this drawback, in this research, a region-based fingerprint recognition method is proposed in which the fingerprints are compared in a pixel-wise manner by computing their correlation coefficient. Therefore, all the attributes of the fingerprint contribute in the matching decision. Such a technique is promising to accurately recognise a partial fingerprint as well as a full fingerprint compared to the minutiae-based fingerprint recognition methods which only concentrateon parts of the fingerprint. The proposed method is based on simple but effective metrics that has been de-fined to compute local similarities which is then combined into a global score and then used to make the match/non-match decision. Extensive experiments over FVC2002 data set has proven the superiority of our method compared to the other well-known techniques reported in literature.

    AB - Partial fingerprints are likely to be fragmentary or low quality, which mandates the development of accurate fingerprint verification algorithms. Two fingerprints should be aligned properly, in order to measure the similarity between them. Moreover, the common fingerprint recognition methods (minutiae-based) only use the limited information that is available. This affects the reliability of the output of the fingerprint recognition system, especially when dealing with partial fingerprints. To overcome this drawback, in this research, a region-based fingerprint recognition method is proposed in which the fingerprints are compared in a pixel-wise manner by computing their correlation coefficient. Therefore, all the attributes of the fingerprint contribute in the matching decision. Such a technique is promising to accurately recognise a partial fingerprint as well as a full fingerprint compared to the minutiae-based fingerprint recognition methods which only concentrateon parts of the fingerprint. The proposed method is based on simple but effective metrics that has been de-fined to compute local similarities which is then combined into a global score and then used to make the match/non-match decision. Extensive experiments over FVC2002 data set has proven the superiority of our method compared to the other well-known techniques reported in literature.

    KW - Biometric

    KW - Partial fingerprint

    KW - Identification

    KW - Authentication

    KW - Local correlation matching technique

    UR - http://www.scopus.com/inward/record.url?scp=84908892414&partnerID=8YFLogxK

    U2 - 10.5220/0005045302750284

    DO - 10.5220/0005045302750284

    M3 - Conference Paper

    SN - 9789897580451

    SP - 275

    EP - 284

    BT - Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014)

    A2 - Obaidat, Mohammad S

    A2 - Holzinger, Andreas

    A2 - Samarati, Pierangela

    PB - Scitepress

    CY - SciTePress Digital Library

    ER -

    Zanganeh O, Bhattacharjee N, Srinivasan B. Partial fingerprint identification through correlation-based approach. In Obaidat MS, Holzinger A, Samarati P, editors, Proceedings of the 11th International Conference on Security and Cryptography (SECRYPT 2014). SciTePress Digital Library: Scitepress. 2014. p. 275 - 284 https://doi.org/10.5220/0005045302750284