Publication Details
3D Face Recognition on Low-Cost Depth Sensors
Drahanský Martin, prof. Ing., Dipl.-Ing., Ph.D. (DITS FIT BUT)
Dvořák Radim, Ing. (DITS FIT BUT)
Provazník Valentine, prof. Ing., Ph.D. (DBME FEEC BUT)
Váňa Jan, Ing. (DITS FIT BUT)
3D face recognition, score-level fusion, biometrics, Gabor filter, Gauss-Laguerre filter
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.
@INPROCEEDINGS{FITPUB10679,
author = "\v{S}t\v{e}p\'{a}n Mr\'{a}\v{c}ek and Martin Drahansk\'{y} and Radim Dvo\v{r}\'{a}k and Valentine Provazn\'{i}k and Jan V\'{a}\v{n}a",
title = "3D Face Recognition on Low-Cost Depth Sensors",
pages = "195--202",
booktitle = "Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG 2014)",
journal = "GI-Edition Lecture Notes in Informatics (LNI)",
volume = 2014,
number = 230,
year = 2014,
location = "Darmstadt, DE",
publisher = "GI - Group for computer science",
ISBN = "978-3-88579-624-4",
ISSN = "1617-5468",
language = "english",
url = "https://www.fit.vut.cz/research/publication/10679"
}