Fast Fingerprint Classification with Deep Neural Network

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

Reducing the number of comparisons in automated fingerprint identification systems is essential when dealing with a large database. Fingerprint classification allows to achieve this goal by dividing fingerprints into several categories, but it presents still some challenges due to the large intra-class variations and the small inter-class variations. The vast majority of the previous methods uses global characteristics, in particular the orientation image, as features of a classifier. This makes the feature extraction stage highly dependent on preprocessing techniques and usually computationally expensive. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage.
Luk

Detaljer

Reducing the number of comparisons in automated fingerprint identification systems is essential when dealing with a large database. Fingerprint classification allows to achieve this goal by dividing fingerprints into several categories, but it presents still some challenges due to the large intra-class variations and the small inter-class variations. The vast majority of the previous methods uses global characteristics, in particular the orientation image, as features of a classifier. This makes the feature extraction stage highly dependent on preprocessing techniques and usually computationally expensive. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage.
OriginalsprogEngelsk
TitelVISAPP - International Conference on Computer Vision Theory and Applications
Publikationsdato2017
StatusAccepteret/In press - 2017
PublikationsartForskning
Peer reviewJa
BegivenhedInternational Conference on Computer Vision Theory and Applications - Porto, Portugal
Varighed: 27 feb. 20171 mar. 2017
Konferencens nummer: 12
http://www.visapp.visigrapp.org

Konference

KonferenceInternational Conference on Computer Vision Theory and Applications
Nummer12
LandPortugal
ByPorto
Periode27/02/201701/03/2017
Internetadresse

Download-statistik

Ingen data tilgængelig
ID: 244496784