How far we can improve micro features based face recognition systems? - AGPIG Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

How far we can improve micro features based face recognition systems?

Résumé

This paper presents improvements for face recognition methods that use LBP descriptor as a main technique in encoding micro features of face images. Our improvements are focused on the feature extraction and dimension reduction steps. In feature extraction, we apply a variant of Local Binary Pattern (LBP) so-called Elliptical Local Binary Pattern (ELBP), which is more efficient than LBP for extracting micro facial features of the human face. ELBP of one pixel is built by thresholding its gray value with its P neighboring pixels on a horizontal ellipse. The dimension reduction step is conducted by using Single Value Decomposition (SVD) based Whitened Principal Component Analysis (WPCA). For performance evaluation of our improvements, we compare them with LBP based, Pattern of Oriented Edge Magnitudes (POEM) based approaches and other popular face recognition systems. The experimental results on state-of-the-art FERET and AR face databases prove the advantages and effectiveness of our improvements.
Fichier non déposé

Dates et versions

hal-00741469 , version 1 (12-10-2012)

Identifiants

  • HAL Id : hal-00741469 , version 1

Citer

Huu Tuan Nguyen, Son Vu, Alice Caplier. How far we can improve micro features based face recognition systems?. IPTA 2012 - 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA 2012), Oct 2012, Istambul, Turkey. pp.n/c. ⟨hal-00741469⟩
197 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More