Texture image classification with Riemannian fisher vectors - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Texture image classification with Riemannian fisher vectors

Résumé

This paper introduces a generalization of the Fisher vectors to the Riemannian manifold. The proposed descriptors, called Riemannian Fisher vectors, are defined first, based on the mixture model of Riemannian Gaussian distributions. Next, their expressions are derived and they are applied in the context of texture image classification. The results are compared to those given by the recently proposed algorithms, bag of Riemannian words and R-VLAD. In addition, the most dis-criminant Riemannian Fisher vectors are identified.
Fichier principal
Vignette du fichier
Ilea16_ICIP.pdf (283.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01379593 , version 1 (11-10-2016)

Identifiants

Citer

Ioana Ilea, Lionel Bombrun, Christian Germain, Romulus Terebes, Monica Borda, et al.. Texture image classification with Riemannian fisher vectors. IEEE International Conference on Image Processing, Sep 2016, Phoenix, United States. pp.3543 - 3547, ⟨10.1109/ICIP.2016.7533019⟩. ⟨hal-01379593⟩
74 Consultations
187 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More