Detail publikace
Fingerprint Area Detection in Fingerprint Images Based on Enhanced Gabor Filtering
DOLEŽEL, M. LODROVÁ, D. BUSCH, C. DRAHANSKÝ, M.
Originální název
Fingerprint Area Detection in Fingerprint Images Based on Enhanced Gabor Filtering
Anglický název
Fingerprint Area Detection in Fingerprint Images Based on Enhanced Gabor Filtering
Jazyk
en
Originální abstrakt
This paper describes a new approach to fingerprint area detection in a digital fingerprint image. This approach was evaluated for real-world scenario, specifically for fingerprints scanned from dactyloscopic fingerprint cards. These images, which compose widely used fingerprint databases, have their specific problems and properties such as handwritten or printed characters, drawings or specific noise in the background or spreaded over the fingerprint itself. Our approach was compared with three other methods and yields significantly better results than the best of the benchmarked methods.
Anglický abstrakt
This paper describes a new approach to fingerprint area detection in a digital fingerprint image. This approach was evaluated for real-world scenario, specifically for fingerprints scanned from dactyloscopic fingerprint cards. These images, which compose widely used fingerprint databases, have their specific problems and properties such as handwritten or printed characters, drawings or specific noise in the background or spreaded over the fingerprint itself. Our approach was compared with three other methods and yields significantly better results than the best of the benchmarked methods.
Dokumenty
BibTex
@inproceedings{BUT34906,
author="Michal {Doležel} and Dana {Lodrová} and Christoph {Busch} and Martin {Drahanský}",
title="Fingerprint Area Detection in Fingerprint Images Based on Enhanced Gabor Filtering",
annote="This paper describes a new approach to fingerprint area detection in a digital
fingerprint image. This approach was evaluated for real-world scenario,
specifically for fingerprints scanned from dactyloscopic fingerprint cards. These
images, which compose widely used fingerprint databases, have their specific
problems and properties such as handwritten or printed characters, drawings or
specific noise in the background or spreaded over the fingerprint itself. Our
approach was compared with three other methods and yields significantly better
results than the best of the benchmarked methods.",
address="Springer Verlag",
booktitle="Bio-Science and Bio-Technology 2010",
chapter="34906",
doi="10.1007/978-3-642-17622-7_23",
edition="NEUVEDEN",
howpublished="print",
institution="Springer Verlag",
year="2010",
month="december",
pages="234--240",
publisher="Springer Verlag",
type="conference paper"
}