ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science
slovenščina

Ocena kvalitete slike prstnega odtisa

Jernej Bule and Matic Tovšak and Peter Peer (2011) Ocena kvalitete slike prstnega odtisa. ERK 2011 . pp. 131-134. ISSN 1581-4572

WarningThere is a more recent version of this item available.
[img]
Preview
 PDF - Published Version
Download (799Kb)

    Abstract

    This paper presents methods for quality measures of fingerprint images. Significant improvement of fingerprint image quality is detected when a fingerprint is first of all captured properly. Further, we present three different methods for fingerprint image quality assessment. The first method is based on pixel intensity, second on minutiae counting and third is a set of methods that are based on a combination of local and global features of fingerprint image (NFIQ algorithm). Presented methods are tested on databases from Fingerprint Verification Competition 2002. Results that we obtained are satisfactory, and point out possible ways to improve fingerprint image quality assessment in our system.

    Item Type: Article
    Keywords: prstni odtisi, kvaliteta slike
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Divisions: Faculty of Computer and Information Science > Computer Vision Laboratory
    Item ID: 1539
    Date Deposited: 27 Sep 2011 03:19
    Last Modified: 27 Sep 2011 03:37
    URI: http://eprints.fri.uni-lj.si/id/eprint/1539

    Available Versions of this Item.

    Actions (login required)

    		 View Item
    EPrints Logo
    ePrints.FRI is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.