Adaptive spatio-color clustering based on the connectedness in a chrominance-luminance space

The paper presents a spatio-color clustering method. First, the RGB space is converted into a spherical representation in order to better reveal the body color vectors of the image. The classification is performed after the color connectedness degrees (CCD) of a color interval which embeds jointly 1) colorimetric information; 2) the probability that a given color is connected (in the image) to a set of similar colors. The chrominance CCDs are analyzed first while the luminance CCDs are studied only when necessary. The number of classes and their shape are adaptive to the image content avoiding any user´s intervention. The method is evaluated visually and quantitatively in terms of quality and in terms of compactness (number of final colors and regions) on the Kodak image database. Our color representation is compared to Ohta and HSV spaces.