Colour texture classification from colour filter array images using various colour spaces

This study focuses on the classification of colour textures acquired by single-sensor colour cameras. In such cameras, the colour filter array (CFA) makes each photosensor sensitive to only one colour component, and CFA images must be demosaiced to estimate the final colour images. We show that demosaicing is detrimental to the textural information because it affects colour texture descriptors such as chromatic co-occurrence matrices (CCMs). However, it remains desirable to take advantage of the chromatic information for colour texture classification. This information is incompletely defined in CFA images, in which each pixel is associated to a single colour component. It is hence a challenge to extract standard colour texture descriptors from CFA images without demosaicing. We propose to form a pair of quarter-size colour images directly from CFA images without any estimation, then to compute the CCMs of these quarter-size images. This allows us to compare textures by means of their CCM-based similarity in texture classification or retrieval schemes, with still the ability to use different colour spaces. Experimental results achieved on benchmark colour texture databases show the effectiveness of the proposed approach for texture classification, and a complexity study highlights its computational efficiency.