Fingerprint comparison is usually based on minutiae matching. The minutiae
considered in automatic identification systems are normally ridge bifurcati
ons and terminations. In this paper we present a set of algorithms for the
extraction of fingerprint minutiae from skeletonized binary images. The goa
l of the present work is the extraction of the real 40-60 minutiae of a fin
gerprint image from the 2000-3000 contained in typical skeletonized and bin
arized images. Besides classical methodologies for minutiae filtering, a ne
w approach is proposed for bridge cleaning based on ridge positions instead
of classical methods based on directional maps. Finally, two novel criteri
a and related algorithms are introduced for validating the endpoints and bi
furcations. Statistical analysis of the results obtained by the proposed ap
proach shows efficient reduction of spurious minutiae. The use of the finge
rprint minutiae extraction algorithms has also been considered in a fingerp
rint identification system in terms of timing and false reject or acceptanc
e rates. The presented minutiae extraction algorithm performs correctly in
dirty areas and on the background as well, making computationally expensive
segmentation algorithms unnecessary. The results are confirmed by visual i
nspections of validated minutiae of the NIST sdb 4 reference fingerprint im
age database. (C) 1999 Pattern Recognition Society. Published by Elsevier S
cience Ltd, All rights reserved.