Statistical hypothesis test for robust classification on the space of covariance matrices - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Statistical hypothesis test for robust classification on the space of covariance matrices

Résumé

This paper introduces a new statistical hypothesis test for robust image classification. First, we introduce the proposed statistical hypothesis test based on the geodesic distance and on the fixed point estimation algorithm. Next, we analyze its properties in the case of the zero-mean multivariate Gaus-sian distribution by studying its asymptotic distribution under the null hypothesis H0. Then, the performance of the proposed classifier is addressed by analyzing its noise robust-ness. Finally, the robust classification method is employed for the classification of simulated Polarimetric Synthetic Aperture Radar images of maritime pine forests.
Fichier principal
Vignette du fichier
Ilea15_ICIP.pdf (156.59 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01228770 , version 1 (13-11-2015)

Identifiants

  • HAL Id : hal-01228770 , version 1

Citer

Ioana Ilea, Lionel Bombrun, Christian Germain, Romulus Terebes, Monica Borda. Statistical hypothesis test for robust classification on the space of covariance matrices. IEEE International Conference on Image Processing (ICIP), Sep 2015, Québec, Canada. ⟨hal-01228770⟩
56 Consultations
288 Téléchargements

Partager

Gmail Facebook X LinkedIn More