Advanced

Wavelet networks for face processing

Krüger, V. LU and Sommer, G. (2002) In Journal of the Optical Society of America A: Optics and Image Science, and Vision 19(6). p.1112-1119
Abstract

Wavelet networks (WNs) were introduced in 1992 as a combination of artificial neural radial basis function (RBF) networks and wavelet decomposition. Since then, however, WNs have received only a little attention. We believe that the potential of WNs has been generally underestimated. WNs have the advantage that the wavelet coefficients are directly related to the image data through the wavelet transform. In addition, the parameters of the wavelets in the WNs are subject to optimization, which results in a direct relation between the represented function and the optimized wavelets, leading to considerable data reduction (thus making subsequent algorithms much more efficient) as well as to wavelets that can be used as an optimized filter... (More)

Wavelet networks (WNs) were introduced in 1992 as a combination of artificial neural radial basis function (RBF) networks and wavelet decomposition. Since then, however, WNs have received only a little attention. We believe that the potential of WNs has been generally underestimated. WNs have the advantage that the wavelet coefficients are directly related to the image data through the wavelet transform. In addition, the parameters of the wavelets in the WNs are subject to optimization, which results in a direct relation between the represented function and the optimized wavelets, leading to considerable data reduction (thus making subsequent algorithms much more efficient) as well as to wavelets that can be used as an optimized filter bank. In our study we analyze some WN properties and highlight their advantages for object representation purposes. We then present a series of results of experiments in which we used WNs for face tracking. We exploit the efficiency that is due to data reduction for face recognition and face-pose estimation by applying the optimized-filter-bank principle of the WNs.

(Less)
Please use this url to cite or link to this publication:
author
and
publishing date
type
Contribution to journal
publication status
published
subject
in
Journal of the Optical Society of America A: Optics and Image Science, and Vision
volume
19
issue
6
pages
8 pages
publisher
Optical Society of America
external identifiers
  • scopus:0041653311
ISSN
1084-7529
DOI
10.1364/JOSAA.19.001112
language
English
LU publication?
no
id
12bdcc98-788d-417a-a5a3-7ce467c1ec5a
date added to LUP
2019-07-08 21:27:18
date last changed
2020-01-13 02:12:49
@article{12bdcc98-788d-417a-a5a3-7ce467c1ec5a,
  abstract     = {<p>Wavelet networks (WNs) were introduced in 1992 as a combination of artificial neural radial basis function (RBF) networks and wavelet decomposition. Since then, however, WNs have received only a little attention. We believe that the potential of WNs has been generally underestimated. WNs have the advantage that the wavelet coefficients are directly related to the image data through the wavelet transform. In addition, the parameters of the wavelets in the WNs are subject to optimization, which results in a direct relation between the represented function and the optimized wavelets, leading to considerable data reduction (thus making subsequent algorithms much more efficient) as well as to wavelets that can be used as an optimized filter bank. In our study we analyze some WN properties and highlight their advantages for object representation purposes. We then present a series of results of experiments in which we used WNs for face tracking. We exploit the efficiency that is due to data reduction for face recognition and face-pose estimation by applying the optimized-filter-bank principle of the WNs.</p>},
  author       = {Krüger, V. and Sommer, G.},
  issn         = {1084-7529},
  language     = {eng},
  month        = {01},
  number       = {6},
  pages        = {1112--1119},
  publisher    = {Optical Society of America},
  series       = {Journal of the Optical Society of America A: Optics and Image Science, and Vision},
  title        = {Wavelet networks for face processing},
  url          = {http://dx.doi.org/10.1364/JOSAA.19.001112},
  doi          = {10.1364/JOSAA.19.001112},
  volume       = {19},
  year         = {2002},
}