Psoriasis Damage Simulation into Synthetic Fingerprint
Zusammenfassung
The goal of this article is to describe method for simulation of damage done by psoriasis. Designed method is based on extracting subjects from real images and then including them into synthetic images. Images are damaged by six different settings. Each setting represents different level of disease severity. Results were verified by visual comparison with real images, consultation with medical doctor, quality measurement methods (NFIQ, FiQiVi), and comparison score (VeriFinger). The most severe damage achieved median score of 38 % (from the reference).
- Vollständige Referenz
- BibTeX
Kanich, O., Košťák, D. & Drahanský, M.,
(2019).
Psoriasis Damage Simulation into Synthetic Fingerprint.
In:
Brömme, A., Busch, C., Dantcheva, A., Rathgeb, C. & Uhl, A.
(Hrsg.),
BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group.
Bonn:
Gesellschaft für Informatik e.V..
(S. 205-212).
@inproceedings{mci/Kanich2019,
author = {Kanich, Ondřej AND Košťák, Davis AND Drahanský, Martin},
title = {Psoriasis Damage Simulation into Synthetic Fingerprint},
booktitle = {BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group},
year = {2019},
editor = {Brömme, Arslan AND Busch, Christoph AND Dantcheva, Antitza AND Rathgeb, Christian AND Uhl, Andreas} ,
pages = { 205-212 },
publisher = {Gesellschaft für Informatik e.V.},
address = {Bonn}
}
author = {Kanich, Ondřej AND Košťák, Davis AND Drahanský, Martin},
title = {Psoriasis Damage Simulation into Synthetic Fingerprint},
booktitle = {BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group},
year = {2019},
editor = {Brömme, Arslan AND Busch, Christoph AND Dantcheva, Antitza AND Rathgeb, Christian AND Uhl, Andreas} ,
pages = { 205-212 },
publisher = {Gesellschaft für Informatik e.V.},
address = {Bonn}
}
| Dateien | Groesse | Format | Anzeige | |
|---|---|---|---|---|
| BIOSIG_2019_paper_23_update.pdf | 425.3Kb | Öffnen |
Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Feedback abschicken
Mehr Information
ISBN: 978-3-88579-690-9
ISSN: 1617-5468
Datum: 2019
Sprache:
(en)
(en)
Typ: Text/Conference Paper

