Publication detail

Face Representation and Tracking Using Gabor Wavelet Networks

ZEMČÍK, P., ŠPANĚL, M.

Original Title

Face Representation and Tracking Using Gabor Wavelet Networks

English Title

Face Representation and Tracking Using Gabor Wavelet Networks

Type

conference paper

Language

en

Original Abstract

This work presents a one of the approaches to human gesture recognition. A method where a discrete face template is represented by linear combination of the 2D odd-Gabor wavelet functions (Gabor Wavelet Network) is proposed. Using wavelet networks, an effective face representation and tracking method is achieved that is robust to changes and deformations of the face image. Possibilities of cooperation between a GWN and others methods for robust facial expressions recognition are also discussed, for example: Principal Component Analysis (PCA) and parameterized models of optical flow.

English abstract

This work presents a one of the approaches to human gesture recognition. A method where a discrete face template is represented by linear combination of the 2D odd-Gabor wavelet functions (Gabor Wavelet Network) is proposed. Using wavelet networks, an effective face representation and tracking method is achieved that is robust to changes and deformations of the face image. Possibilities of cooperation between a GWN and others methods for robust facial expressions recognition are also discussed, for example: Principal Component Analysis (PCA) and parameterized models of optical flow.

Keywords

Image, Object representation, Feature-based, Template-based, 2D Gabor wavelet functions, Gabor Wavelet Networks, Facial features, Tracking, Facial expressions, Parameterized models of optical flow, Principal Component Analysis

RIV year

2003

Released

22.04.2003

Location

Budmerice

Pages from

163

Pages to

169

Pages count

7

Documents

BibTex


@inproceedings{BUT10927,
  author="Michal {Španěl} and Pavel {Zemčík}",
  title="Face Representation and Tracking Using Gabor Wavelet Networks",
  annote="This work presents a one of the approaches to human gesture
recognition. A method where a discrete face template is represented by
linear combination of the 2D odd-Gabor wavelet functions (Gabor Wavelet
Network) is proposed. Using wavelet networks, an effective face
representation and tracking method is achieved that is robust to
changes and deformations of the face image. Possibilities of
cooperation between a GWN and others methods for robust facial
expressions recognition are also discussed, for example: Principal
Component Analysis (PCA) and parameterized models of optical flow.
", booktitle="Proceedings of the Central European Seminar on Computer Graphics", chapter="10927", year="2003", month="april", pages="163--169", type="conference paper" }