Detail publikace

3D Face Recognition on Low-Cost Depth Sensors

Originální název

3D Face Recognition on Low-Cost Depth Sensors

Anglický název

3D Face Recognition on Low-Cost Depth Sensors

Jazyk

en

Originální 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.

Anglický 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.

BibTex


@inproceedings{BUT111626,
  author="Štěpán {Mráček} and Martin {Drahanský} and Radim {Dvořák} and Ivo {Provazník} and Jan {Váňa}",
  title="3D Face Recognition on Low-Cost Depth Sensors",
  annote="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.",
  address="GI - Group for computer science",
  booktitle="Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG 2014)",
  chapter="111626",
  edition="NEUVEDEN",
  howpublished="print",
  institution="GI - Group for computer science",
  number="230",
  year="2014",
  month="september",
  pages="195--202",
  publisher="GI - Group for computer science",
  type="conference paper"
}