Comparison of color imaging vs. hyperspectral imaging for texture classification

•Hyperspectral and color imaging are compared for texture analysis in the visible spectrum•Opponent component approaches significantly improve accuracy compared to marginal ones•Hyperspectral imaging outperforms color imaging when an opponent component approach is applied•Color imaging reaches better accuracies than hyperspectral in a marginal context•A challenging hyperspectral texture dataset is proposed to assess the classification performance