Unsupervised 2D multiband histogram clustering and region for color image segmentation

A segmentation method for color images is presented in this work. A morphological unsupervised 2D multiband histogram clustering provides an initial segmentation of the image. Region information is then used and a novel technique is introduced to simplify the region adjacency graph by merging candidate regions until the stabilization of a "good" segmentation criterion. Merged regions are refined by a color watershed. The whole method requires the definition of only one single parameter which acts as a multiscale parameter.