Advanced

Gabor wavelet networks for efficient head pose estimation

Krüger, Volker LU and Sommer, Gerald (2002) In Image and Vision Computing 20(9-10). p.665-672
Abstract

In this paper, we first introduce the Gabor wavelet network (GWN) as a model-based approach for effective and efficient object representation. GWNs combine the advantages of the continuous wavelet transform with RBF networks. They have additional advantages such as invariance to some degree with respect to affine deformations. The use of Gabor filters enables the coding of geometrical and textural object features. Gabor filters as a model for local object features ensure considerable data reduction while at the same time allowing any desired precision of the object representation ranging from sparse to photo-realistic representation. As an application we present an approach for the estimation of head pose based on the GWNs. Feature... (More)

In this paper, we first introduce the Gabor wavelet network (GWN) as a model-based approach for effective and efficient object representation. GWNs combine the advantages of the continuous wavelet transform with RBF networks. They have additional advantages such as invariance to some degree with respect to affine deformations. The use of Gabor filters enables the coding of geometrical and textural object features. Gabor filters as a model for local object features ensure considerable data reduction while at the same time allowing any desired precision of the object representation ranging from sparse to photo-realistic representation. As an application we present an approach for the estimation of head pose based on the GWNs. Feature information is encoded in the wavelet coefficients. An artificial neural network is then used to compute the head pose from the wavelet coefficients.

(Less)
Please use this url to cite or link to this publication:
author
and
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Gabor wavelet networks, Pose estimation
in
Image and Vision Computing
volume
20
issue
9-10
pages
8 pages
publisher
Elsevier
external identifiers
  • scopus:0036682749
ISSN
0262-8856
DOI
10.1016/S0262-8856(02)00056-2
language
English
LU publication?
no
id
953e1f1f-b993-4f00-af1a-37d6d76b6752
date added to LUP
2019-07-08 21:27:57
date last changed
2020-08-05 05:28:07
@article{953e1f1f-b993-4f00-af1a-37d6d76b6752,
  abstract     = {<p>In this paper, we first introduce the Gabor wavelet network (GWN) as a model-based approach for effective and efficient object representation. GWNs combine the advantages of the continuous wavelet transform with RBF networks. They have additional advantages such as invariance to some degree with respect to affine deformations. The use of Gabor filters enables the coding of geometrical and textural object features. Gabor filters as a model for local object features ensure considerable data reduction while at the same time allowing any desired precision of the object representation ranging from sparse to photo-realistic representation. As an application we present an approach for the estimation of head pose based on the GWNs. Feature information is encoded in the wavelet coefficients. An artificial neural network is then used to compute the head pose from the wavelet coefficients.</p>},
  author       = {Krüger, Volker and Sommer, Gerald},
  issn         = {0262-8856},
  language     = {eng},
  month        = {08},
  number       = {9-10},
  pages        = {665--672},
  publisher    = {Elsevier},
  series       = {Image and Vision Computing},
  title        = {Gabor wavelet networks for efficient head pose estimation},
  url          = {http://dx.doi.org/10.1016/S0262-8856(02)00056-2},
  doi          = {10.1016/S0262-8856(02)00056-2},
  volume       = {20},
  year         = {2002},
}