Detail výsledku

3D Face Recognition on Low-Cost Depth Sensors

MRÁČEK, Š.; DRAHANSKÝ, M.; DVOŘÁK, R.; PROVAZNÍK, V.; VÁŇA, J. 3D Face Recognition on Low-Cost Depth Sensors. In Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG 2014). GI-Edition Lecture Notes in Informatics (LNI). Darmstadt: GI - Group for computer science, 2014. no. 230, p. 195-202. ISBN: 978-3-88579-624-4. ISSN: 1617-5468.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Mráček Štěpán, Ing., Ph.D., UIFS (FIT), UITS (FIT)
Drahanský Martin, prof. Ing., Ph.D., RE-OPPaTT (RE), UITS (FIT)
Dvořák Radim, Ing., Ph.D.
Provazník Valentýna, prof. Ing., Ph.D., UBMI (FEKT)
Váňa Jan, Ing., UIFS (FIT)
Abstrakt

This paper deals with the biometric recognition of 3D faces with the emphasis on the low-cost depth sensors; such are Microsoft Kinect and SoftKinetic DS325. The presented approach is based on the score-level fusion of individual recognition units. Each unit processes the input face mesh and produces a curvature, depth, or texture representation. This image representation is further processed by specific Gabor or Gauss-Laguerre complex filter. The absolute response is then projected to lower-dimension representations and the feature vector is thus extracted. Comparison scores of individual recognition units are combined using transformation-based, classifier-based, or density-based score-level fusion. The results suggest that even poor quality low-resolution scans containing holes and noise might be successfully used for recognition in relatively small databases.

Klíčová slova

3D face recognition, score-level fusion, biometrics, Gabor filter, Gauss-Laguerre filter

Rok
2014
Strany
195–202
Časopis
GI-Edition Lecture Notes in Informatics (LNI), roč. 2014, č. 230, ISSN 1617-5468
Sborník
Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG 2014)
Konference
Biometrics Special Interest Group 2014
ISBN
978-3-88579-624-4
Vydavatel
GI - Group for computer science
Místo
Darmstadt
UT WoS
000412427900017
EID Scopus
2-s2.0-84919343433
BibTeX 
@inproceedings{BUT111626,
  author="Štěpán {Mráček} and Martin {Drahanský} and Radim {Dvořák} and Valentýna {Provazník} and Jan {Váňa}",
  title="3D Face Recognition on Low-Cost Depth Sensors",
  booktitle="Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG 2014)",
  year="2014",
  journal="GI-Edition Lecture Notes in Informatics (LNI)",
  volume="2014",
  number="230",
  pages="195--202",
  publisher="GI - Group for computer science",
  address="Darmstadt",
  isbn="978-3-88579-624-4",
  issn="1617-5468",
  url="https://www.fit.vut.cz/research/publication/10679/"
}
Soubory
Projekty
Centrum excelence IT4Innovations, MŠMT, Operační program Výzkum a vývoj pro inovace, ED1.1.00/02.0070, zahájení: 2011-01-01, ukončení: 2015-12-31, ukončen
Nástroje a metody zpracování videa a obrazu pro boj s terorismem, MV, Program bezpečnostního výzkumu České republiky 2010 - 2015, VG20102015006, zahájení: 2010-10-01, ukončení: 2015-09-30, ukončen
Spolehlivost a bezpečnost v IT, VUT, Vnitřní projekty VUT, FIT-S-14-2486, zahájení: 2014-01-01, ukončení: 2016-12-31, ukončen
Verifikace a optimalizace počítačových systémů, VUT, Vnitřní projekty VUT, FIT-S-12-1, zahájení: 2012-01-01, ukončení: 2014-12-31, ukončen
Výzkumné skupiny
Security Technology Research and Development (VZ STRaDe)
Pracoviště
Ústav inteligentních systémů (UITS)
Nahoru