Joint Linear-Circular Stochastic Models for Texture Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Joint Linear-Circular Stochastic Models for Texture Classification

Résumé

In this paper, we investigate both linear and circular stochastic models in the context of texture discrimination. These models aim at representing the magnitudes and orientations obtained by a complex wavelet decomposition, such as the steerable pyramid. The novelty consists in considering specific parametric models for circular data such as Von Mises and Psi-distributions to describe the distributions of orientations. Particular attention is paid to the choice of a metric and to its adequation to the models. Indexation experiments are conducted to quantitatively evaluate the performances of the proposed models and of the chosen matrics, i.e. the L1 and Kullback-Leibler metrics.
Fichier non déposé

Dates et versions

hal-00391314 , version 1 (03-06-2009)

Identifiants

  • HAL Id : hal-00391314 , version 1

Citer

Marie-Cécile Péron, Youssef Stitou, Yannick Berthoumieu, Jean-Pierre da Costa, Christian Germain. Joint Linear-Circular Stochastic Models for Texture Classification. ICASSP 2009, Apr 2009, Taiwan. pp.3822. ⟨hal-00391314⟩
73 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More