A wavelet subspace method for real-time face tracking
(2004) In Real-Time Imaging 10(6). p.339-350- Abstract
In this article, we present a new method for visual face tracking that is carried out in a wavelet subspace. Initially, a wavelet representation for the face template is created, which spans a low-dimensional subspace of the image space. The video sequence frames, where the face is tracked, are then orthogonally projected into this subspace. This can be done efficiently through a small number of applications of the wavelet filters. All further computations are performed in the low-dimensional wavelet subspace, allowing real-time processing. An effective performance assessment is carried out to show robustness with respect to facial expression and affine deformations, as well as the efficiency of our method, which allows real-time face... (More)
In this article, we present a new method for visual face tracking that is carried out in a wavelet subspace. Initially, a wavelet representation for the face template is created, which spans a low-dimensional subspace of the image space. The video sequence frames, where the face is tracked, are then orthogonally projected into this subspace. This can be done efficiently through a small number of applications of the wavelet filters. All further computations are performed in the low-dimensional wavelet subspace, allowing real-time processing. An effective performance assessment is carried out to show robustness with respect to facial expression and affine deformations, as well as the efficiency of our method, which allows real-time face tracking.
(Less)
- author
- Feris, Rogerio S. ; Krueger, Volker LU and Cesar, Roberto M.
- publishing date
- 2004-12-01
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Real-Time Imaging
- volume
- 10
- issue
- 6
- pages
- 12 pages
- publisher
- Academic Press
- external identifiers
-
- scopus:11844276580
- ISSN
- 1077-2014
- DOI
- 10.1016/j.rti.2004.06.002
- language
- English
- LU publication?
- no
- id
- ef1d8ce9-fc1d-49e7-a13c-b2eae89d7cef
- date added to LUP
- 2019-07-08 21:21:32
- date last changed
- 2022-01-31 23:22:07
@article{ef1d8ce9-fc1d-49e7-a13c-b2eae89d7cef, abstract = {{<p>In this article, we present a new method for visual face tracking that is carried out in a wavelet subspace. Initially, a wavelet representation for the face template is created, which spans a low-dimensional subspace of the image space. The video sequence frames, where the face is tracked, are then orthogonally projected into this subspace. This can be done efficiently through a small number of applications of the wavelet filters. All further computations are performed in the low-dimensional wavelet subspace, allowing real-time processing. An effective performance assessment is carried out to show robustness with respect to facial expression and affine deformations, as well as the efficiency of our method, which allows real-time face tracking.</p>}}, author = {{Feris, Rogerio S. and Krueger, Volker and Cesar, Roberto M.}}, issn = {{1077-2014}}, language = {{eng}}, month = {{12}}, number = {{6}}, pages = {{339--350}}, publisher = {{Academic Press}}, series = {{Real-Time Imaging}}, title = {{A wavelet subspace method for real-time face tracking}}, url = {{http://dx.doi.org/10.1016/j.rti.2004.06.002}}, doi = {{10.1016/j.rti.2004.06.002}}, volume = {{10}}, year = {{2004}}, }