Incorporating two first order moments into LBP-based operator for texture categorization - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Incorporating two first order moments into LBP-based operator for texture categorization

Thanh Phuong Nguyen
Antoine Manzanera

Résumé

Within different techniques for texture modelling and recog-nition, local binary patterns and its variants have received much interest in recent years thanks to their low computational cost and high discrim-ination power. We propose a new texture description approach, whose principle is to extend the LBP representation from the local gray level to the regional distribution level. The region is represented by pre-defined structuring element, while the distribution is approximated using the two first statistical moments. Experimental results on four large texture databases, including Outex, KTH-TIPS 2b, CUReT and UIUC show that our approach significantly improves the performance of texture represen-tation and classification with respect to comparable methods.
Fichier principal
Vignette du fichier
TwoFirstMomentsLBP.pdf (2.01 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01118284 , version 1 (18-02-2015)

Identifiants

  • HAL Id : hal-01118284 , version 1

Citer

Thanh Phuong Nguyen, Antoine Manzanera. Incorporating two first order moments into LBP-based operator for texture categorization. ACCV Workshop: Robust local descriptors for computer vision, Nov 2014, Singapour, Singapore. ⟨hal-01118284⟩
39 Consultations
109 Téléchargements

Partager

Gmail Facebook X LinkedIn More