Analysis of performance of palmprint matching with enforced sparsity

Omar Nibouche, Jianmin Jiang, Paul Trundle

    Research output: Contribution to journalArticle

    14 Citations (Scopus)

    Abstract

    In this paper, a new palmprint matching system based on the extraction of feature points is suggested. Using a scale-space representation, the points in question are corners formed by the intersection of creases and lines. Unlike minutiae, such points can still be extracted even on low resolution palmprints. Matching is carried out using an SVD factorisation of a proximity matrix and takes account of the coordinates of the detected points and their local texture. Our experiments have yielded some very good results evidenced by an EER of 0.10%.
    Original languageEnglish
    Pages (from-to)348-355
    JournalDigital Signal Processing
    Volume22
    Issue number2
    DOIs
    Publication statusPublished - Mar 2012

    Fingerprint Dive into the research topics of 'Analysis of performance of palmprint matching with enforced sparsity'. Together they form a unique fingerprint.

  • Cite this