Abstract:
Fingerprints are widely used in biometric
techniques for automatic personal identification
work. In this paper, a fingerprint recognition system
is developed to identify a person according to
fingerprint image on Myanmar National Registration
Cards (NRCs). Generally, fingerprint identification
approaches are minutiae-based and texture-based.
Although the minutiae-based method is popular and
extensively used method for fingerprint
identification, it shows poor performance for low
quality images. In proposed system, the texturebased
approach for fingerprint recognition using
Discrete Wavelet Transform (DWT) is developed. To
reduce the search time and computational
complexity, the proposed system classifies the
fingerprint types according to ridges direction by
singular candidate analysis using an extended
relational graph. And then, the system finds the local
features of the fingerprint using DWT and it is
compared to the subset of the database containing
that type of fingerprints using Euclidean distance
metric. The performance of the proposed system can
be evaluated by measuring its False Reject Rate
(FRR) and False Accept Rate (FAR). The
effectiveness of the proposed system can be
confirmed through the experimental results.
