Logo des Repositoriums

Auflistung nach Schlagwort "Fingerprint recognition"

1 - 5 von 5
  • Konferenzbeitrag
    Contactless Fingerprints: Differential Performance for Fingers of Varying Size and Ridge Density
    (BIOSIG 2023, 2023) Carson King, Evan Garrett
    The match performance of contactless fingerprint probes compared to contact-based galleries has increased accuracy. This performance, along with convenience of use, is encouraging the utilization of contactless fingerprint collection methods. However, issues with differential performance for different demographics may still exist. Past works focused mainly on the interoperability of contactless prints with smartphone applications and kiosk devices. This paper focuses on the differential performance of genuine match scores based on the demographic of finger size, ridge density, and total ridge count. Distribution of genuine match scores shows a correlation between an increase in genuine match scores and these variables in contactless smartphone collection methods with the largest correlation appearing in finger size.
  • Textdokument
    Fingerprint Damage Localizer and Detector of Skin Diseases from Fingerprint Images
    (BIOSIG 2017, 2017) Barotova,Stepanka; Drahansky,Martin
    This article describes a novel approach for detection and classification of skin diseases in fingerprints using three methods - Block Orientation Field, Histogram Analysis and Flood Fill. The combination of these methods brings a surprising results and using a rule descriptor for selected skin diseases, we are able to classify the disease into a group or concrete name.
  • Konferenzbeitrag
    Fundamental Study of Neonate Fingerprint Recognition Using Fingerprint Classification
    (BIOSIG 2022, 2022) Yoshinori Koda, Haruki Imai
    UNICEF reported that many of the 2.4 million deaths within 28 days of birth were preventable with appropriate vaccination. There are several reasons why babies cannot be vaccinated, for example, the medical staff does not have appropriate vaccination history management to control who and when they should be vaccinated. To properly manage vaccination history and promote its widespread use, personal identification after birth is essential, and a neonate fingerprint identification technology could be one of the solutions. In this paper, we develop a fingerprint scanner with a 2,674ppi high-resolution CMOS sensor specifically designed to acquire neonatal fingerprints by integrating positive comments from users in the research field on the previous prototype. We also propose a neonate fingerprint identification method based on fingerprint classification.
  • Konferenzbeitrag
    Towards Contactless Fingerprint Presentation Attack Detection using Algorithms from the Contact-based Domain
    (BIOSIG 2023, 2023) Jannis Priesnitz, Roberto Casula
    In this work, we investigate whether contact-based fingerprint Presentation Attack Detection (PAD) methods can generalize to the contactless domain. To this end, we selected a state-of-the-art patch-based fingerprint PAD algorithm which achieved high detection performance in the contact-based domain and adapted it for contactless fingerprints. We train and test the method using three contactless fingerprint databases and evaluate its generalization capabilities using Leave-One-Out (LOO) protocols. Further, we acquired a new PAD database and use it in a cross-database evaluation. The adopted method shows low error rates in most scenarios and can generalize to unseen contactless presentation attacks.
  • Konferenzbeitrag
    Utility prediction performance of finger image quality assessment software
    (BIOSIG 2023, 2023) Olaf Henniger
    A biometric sample is the more utile for biometric recognition the greater the distance between the sample-specific non-mated and mated comparison score distributions. Finger image quality scores turn out to be only weakly correlated with the observed utility. This is worth investigating because finger image quality assessment software is widely used to predict the biometric utility of finger images in many public-sector applications. This paper shows that a weak correlation between predicted and observed utility does not matter if the quality scores are used to decide whether to discard or retain biometric samples for further processing. The important point is that useful samples are not mistakenly discarded or less useful samples are not mistakenly retained. This can be measured by quality-assessment false positive and false negative rates. In cost-benefit analyses, these metrics can be used to chose suitable quality-score thresholds for the use cases at hand.