Fingerprint indexing based on combination of novel minutiae triplet features

W. Zhou, J. Hu, S. Wang, I.R. Petersen, Mohammed Bennamoun

    Research output: Chapter in Book/Conference paperConference paperpeer-review

    11 Citations (Scopus)


    © Springer International Publishing Switzerland 2014. Fingerprint indexing is a process of pre-filtering the template database before matching. The most common features used for fingerprint indexing are based on minutiae triplets. In this paper, we investigated the indexing performance based on some commonly used features of minutiae triplets and proposed to combine these features with some novel features of minutiae triplets for fingerprint indexing. Experiments on FVC 2000 DB2a and 2002 DB1a show that the proposed indexing method can perform better than state-of-the-art schemes for full fingerprint indexing, meanwhile, experimental results on NIST SD 14 show that the performance is improved significantly after the new features are added to the feature space, and is fairly good even for partial fingerprint indexing.
    Original languageEnglish
    Title of host publicationLecture Notes in Computer Science
    Subtitle of host publicationNetwork and System Security
    EditorsMan Ho Au, Barbara Carminati, C.-C. Jay Kuo
    PublisherSpringer International Publishing Switzerland
    ISBN (Electronic)9783319116983
    ISBN (Print)9783319116976
    Publication statusPublished - 2014
    Event8th International Conference on Network and System Security (NSS) - China, Xi'an, China
    Duration: 15 Oct 201417 Oct 2014


    Conference8th International Conference on Network and System Security (NSS)


    Dive into the research topics of 'Fingerprint indexing based on combination of novel minutiae triplet features'. Together they form a unique fingerprint.

    Cite this