HAL : hal-00452438, version 1

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

International Conference on Computer Vision and Graphics (ICCVG 04), Warsaw : Pologne (2004)

Two-Dimensional-Oriented Linear Discriminant Analysis for Face Recognition

Muriel Visani 1, Christophe Garcia 2, Jean-Michel Jolion 1

(09/2004)

In this paper, a new statistical projection-based method called Two-Dimensional- Oriented Linear Discriminant Analysis (2DO-LDA) is presented. While in the Fisherfaces method the 2D image matrices are first transformed into 1D vectors by merging their rows of pixels, 2DO-LDA is directly applied on matrices, as 2D-PCA. Within and between-class image covariance matrices are generalized, and 2DO-LDA aims at finding a projection space jointly maximizing the second and minimizing the first by considering a generalized Fisher criterion defined on image matrices. A series of experiments was performed on various face image databases in order to evaluate and compare the effectiveness and robustness of 2DO-LDA to 2D-PCA and the Fisherfaces method. The experimental results indicate that 2DO-LDA is more efficient than both 2D-PCA and LDA when dealing with variations in lighting conditions, facial expression and head pose.

1 :	Laboratoire d'InfoRmatique en Images et Systèmes d'Information (LIRIS)
	CNRS : UMR5205 – Université Claude Bernard - Lyon I – Université Lumière - Lyon II – Institut National des Sciences Appliquées (INSA) - Lyon – Ecole Centrale de Lyon
2 :	France Télécom R&D
	France Télécom

Domaine

:

Informatique/Vision par ordinateur et reconnaissance de formes

Mots Clés : Face recognition – Discriminant Analysis – supervised classification – image analysis

hal-00452438, version 1

http://hal.archives-ouvertes.fr/hal-00452438

oai:hal.archives-ouvertes.fr:hal-00452438

Contributeur : Muriel Visani <>

Soumis le : Mardi 2 Février 2010, 14:05:06

Dernière modification le : Mardi 2 Février 2010, 14:51:40