Ghent University Academic Bibliography

Advanced

Best view selection with geometric feature based face recognition

Francis Deboeverie UGent, Peter Veelaert UGent and Wilfried Philips UGent (2012) IEEE International Conference on Image Processing, Proceedings. p.1461-1464
abstract
Nowadays, an important problem in multi-camera systems is how to select the camera with the best frontal view of a person in order to visualize to an observer. Therefore, we present a minimum score based criterion for best view selection, based on face recognition with geometric features. In this approach, faces are represented with Curve Edge Maps (CEMs), which are collections of polynomial curves with a convex region. Face recognition is performed by matching face CEMs driven by histograms of intensities and histograms of relative positions. The resulting face recognition scores are employed as quality-of-view measures. They indicate whether or not persons are seen by cameras in frontal view. Experiments show that the method is robust and efficient when selecting the best view in a multi-camera system. Furthermore, our method outperforms view selection based on face detection only.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
polynomial fitting, best view selection, contour segmentation, L-infinity norm, face recognition
in
IEEE International Conference on Image Processing, Proceedings
pages
1461 - 1464
publisher
IEEE
place of publication
Piscataway, NJ, USA
conference name
IEEE International Conference on Image Processing (ICIP - 2012)
conference location
Orlando, Florida, USA
conference start
2012-09-30
conference end
2012-10-03
Web of Science type
Proceedings Paper
Web of Science id
000319334901134
ISSN
1522-4880
ISBN
9781467325325
language
English
UGent publication?
yes
classification
P1
copyright statement
I have transferred the copyright for this publication to the publisher
id
2102448
handle
http://hdl.handle.net/1854/LU-2102448
date created
2012-05-09 12:52:39
date last changed
2013-10-22 11:06:21
@inproceedings{2102448,
  abstract     = {Nowadays, an important problem in multi-camera systems is how to select the camera with the best frontal view of a person in order to visualize to an observer. Therefore, we present a minimum score based criterion for best view selection, based on face recognition with geometric features. In this approach, faces are represented with Curve Edge Maps (CEMs), which are collections of polynomial curves with a convex region. Face recognition is performed by matching face CEMs driven by histograms of intensities and histograms of relative positions. The resulting face recognition scores are employed as quality-of-view measures. They indicate whether or not persons are seen by cameras in frontal view. Experiments show that the method is robust and ef\unmatched{fb01}cient when selecting the best view in a multi-camera system. Furthermore, our method outperforms view selection based on face detection only.},
  author       = {Deboeverie, Francis and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {IEEE International Conference on Image Processing, Proceedings},
  isbn         = {9781467325325},
  issn         = {1522-4880},
  keyword      = {polynomial \unmatched{fb01}tting,best view selection,contour segmentation,L-infinity norm,face recognition},
  language     = {eng},
  location     = {Orlando, Florida, USA},
  pages        = {1461--1464},
  publisher    = {IEEE},
  title        = {Best view selection with geometric feature based face recognition},
  year         = {2012},
}

Chicago
Deboeverie, Francis, Peter Veelaert, and Wilfried Philips. 2012. “Best View Selection with Geometric Feature Based Face Recognition.” In IEEE International Conference on Image Processing, Proceedings, 1461–1464. Piscataway, NJ, USA: IEEE.
APA
Deboeverie, F., Veelaert, P., & Philips, W. (2012). Best view selection with geometric feature based face recognition. IEEE International Conference on Image Processing, Proceedings (pp. 1461–1464). Presented at the IEEE International Conference on Image Processing (ICIP - 2012), Piscataway, NJ, USA: IEEE.
Vancouver
1.
Deboeverie F, Veelaert P, Philips W. Best view selection with geometric feature based face recognition. IEEE International Conference on Image Processing, Proceedings. Piscataway, NJ, USA: IEEE; 2012. p. 1461–4.
MLA
Deboeverie, Francis, Peter Veelaert, and Wilfried Philips. “Best View Selection with Geometric Feature Based Face Recognition.” IEEE International Conference on Image Processing, Proceedings. Piscataway, NJ, USA: IEEE, 2012. 1461–1464. Print.