Fingerprint Recognition Using Hybrid Matching Algorithm
No Thumbnail Available
Date
2003-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Fingerprint matching is one of the most important problems in fingerprint recognition
system. Generally, fingerprint matching algorithm can be classified into two: minutiae based
and non‐minutiae based. In minutiae based matching, ridge endings and ridge bifurcations
are used as discriminative features for matching, but in non‐minutiae based, features other
than minutiae are used.
Hybrid approaches by combining minutiae with other non‐minutiae based matching
methods are used to improve fingerprint matching methods. In this paper, alignment‐based
elastic matching algorithm, is used for minutiae based matching and new non‐minutiae
method proposed which solve the shortcomings of the algorithms proposed by Jain et.al.
The experiment was done on 320 fingerprints of Fingerprint Verification Competition 2002
set‐B databases and showed that the hybrid matching algorithm improved the Equal Error
Rate from ~11.8 % to 7.55% than the minutiae based matching algorithm.
Keyword: Image processing, Fingerprint recognition, local orientation, local frequency,
minutiae, absolute average deviation from the mean, Gabor filter.
Description
Keywords
Image processing, Fingerprint recognition, local orientation, local frequency, minutiae, absolute average deviation from the mean, Gabor filter