Wavelet subspace method for real-time face tracking
Krüger, Volker LU
and Feris, Rogerio S.
(2001)
23rd German Association for Pattern Recognition Symposium, DAGM 2001
In Lecture Notes in Computer Science
2191.
p.186-193
- Abstract
In this article we present a new method for visual face tracking that is carried out in wavelet subspace. Firstly, a waveletre presentation for the face template is created, which spans a low dimensional subspace of the image space. The wavelet representation of the face is a point in this wavelet subspace. The video sequence frames in which the face is tracked are orthogonally projected into this low-dimensional subspace. This can be done efficiently through asmall number of local projections of the wavelet functions. All further computations are then performed in the low-dimensional subspace.The wavelet subspace inherets its invariance to rotation, scale and translation from the wavelets; shear invariance can also be achieved, which... (More)
In this article we present a new method for visual face tracking that is carried out in wavelet subspace. Firstly, a waveletre presentation for the face template is created, which spans a low dimensional subspace of the image space. The wavelet representation of the face is a point in this wavelet subspace. The video sequence frames in which the face is tracked are orthogonally projected into this low-dimensional subspace. This can be done efficiently through asmall number of local projections of the wavelet functions. All further computations are then performed in the low-dimensional subspace.The wavelet subspace inherets its invariance to rotation, scale and translation from the wavelets; shear invariance can also be achieved, which makes the subspace invariant to affine deformations.
(Less)
- author
- Krüger, Volker
LU
and Feris, Rogerio S.
- publishing date
- 2001-01-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Face tracking, Wavelet decomposition, Wavelet network
- host publication
- Pattern Recognition : 23rd DAGM Symposium Munich, Germany, September 12–14, 2001 Proceedings - 23rd DAGM Symposium Munich, Germany, September 12–14, 2001 Proceedings
- series title
- Lecture Notes in Computer Science
- editor
- Radig, Bernd and Florczyk, Stefan
- volume
- 2191
- pages
- 8 pages
- publisher
- Springer
- conference name
- 23rd German Association for Pattern Recognition Symposium, DAGM 2001
- conference location
- Munich, Germany
- conference dates
- 2001-09-12 - 2001-09-14
- external identifiers
-
- scopus:84945267812
- ISSN
- 1611-3349
- 0302-9743
- ISBN
- 3540425969
- DOI
- 10.1007/3-540-45404-7_25
- language
- English
- LU publication?
- no
- id
- 1f9635a6-d637-4695-b19c-6020e52d1ed7
- date added to LUP
- 2019-07-08 21:28:17
- date last changed
- 2025-04-04 14:05:27
@inproceedings{1f9635a6-d637-4695-b19c-6020e52d1ed7,
abstract = {{<p>In this article we present a new method for visual face tracking that is carried out in wavelet subspace. Firstly, a waveletre presentation for the face template is created, which spans a low dimensional subspace of the image space. The wavelet representation of the face is a point in this wavelet subspace. The video sequence frames in which the face is tracked are orthogonally projected into this low-dimensional subspace. This can be done efficiently through asmall number of local projections of the wavelet functions. All further computations are then performed in the low-dimensional subspace.The wavelet subspace inherets its invariance to rotation, scale and translation from the wavelets; shear invariance can also be achieved, which makes the subspace invariant to affine deformations.</p>}},
author = {{Krüger, Volker and Feris, Rogerio S.}},
booktitle = {{Pattern Recognition : 23rd DAGM Symposium Munich, Germany, September 12–14, 2001 Proceedings}},
editor = {{Radig, Bernd and Florczyk, Stefan}},
isbn = {{3540425969}},
issn = {{1611-3349}},
keywords = {{Face tracking; Wavelet decomposition; Wavelet network}},
language = {{eng}},
month = {{01}},
pages = {{186--193}},
publisher = {{Springer}},
series = {{Lecture Notes in Computer Science}},
title = {{Wavelet subspace method for real-time face tracking}},
url = {{http://dx.doi.org/10.1007/3-540-45404-7_25}},
doi = {{10.1007/3-540-45404-7_25}},
volume = {{2191}},
year = {{2001}},
}