Color texture classification method based on a statistical multi-model and geodesic distance

Ahmed Drissi El Maliani (1) , Mohammed El Hassouni (2) , Y Berthoumieu (3) , D Aboutajdine (2)

1 L.I.M. - Laboratoire Informatique et Modélisation
2 GSCM-LRIT - Laboratoire de Recherche en Informatique et Télécommunications [Rabat]
3 IMS - Laboratoire de l'intégration, du matériau au système

In this letter, we propose a novel color texture classification method based on statistical characterization. The approach consists in modeling complex wavelet coefficients of both luminance and chrominance components separately leading to a multi-modeling approach. The copula theory allows to take into account the spatial dependencies which exist within the intra-luminance sub-bands via the luminance model M L , and also between the inter-chrominance subband coefficients via the chrominance model M Cr. The multi-model, i.e M L and M Cr , is used to develop a Bayesian classifier based on the softmax principal. To derive the classifier, we propose a closed-form expression for the Rao geodesic distance between two copulas. Experiments on two sub-families of luminance-chrominance color spaces namely Lab and HSV have been carried out for a wide range of color texture databases. The combination of different statistical sub-models show that the multi-modeling performs better than some existing methods in term of classification rates.

Mots clés: Color texture; wavelet representation; Rao geodesic distance; Bayesian classification

Domaines: Traitement des images [eess.IV]; Modélisation et simulation

Ahmed Drissi El Maliani, Mohammed El Hassouni, Y Berthoumieu, D Aboutajdine. Color texture classification method based on a statistical multi-model and geodesic distance. Journal of Visual Communication and Image Representation, 2014, ⟨10.1016/j.jvcir.2014.06.004⟩. ⟨hal-01312729⟩