Abstract
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.
Originalsprog | Engelsk |
---|---|
Titel | VISiGRAPP 2017 : Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
Redaktører | Francisco Imai, Alain Tremeau, Jose Braz |
Vol/bind | 5 |
Forlag | SCITEPRESS Digital Library |
Publikationsdato | 2017 |
Sider | 202-209 |
ISBN (Trykt) | 978-989-758-226-4 |
DOI | |
Status | Udgivet - 2017 |
Begivenhed | International Conference on Computer Vision Theory and Applications - Porto, Portugal Varighed: 27 feb. 2017 → 1 mar. 2017 Konferencens nummer: 12 http://www.visapp.visigrapp.org |
Konference
Konference | International Conference on Computer Vision Theory and Applications |
---|---|
Nummer | 12 |
Land/Område | Portugal |
By | Porto |
Periode | 27/02/2017 → 01/03/2017 |
Internetadresse |