Segmentation of color images by clustering 2D histogram and merging regions

An hybrid segmentation method for color images is presented in this work. It combines 2D histogram clustering to produce segmentation maps fused together providing an initial unsupervised clustering of the dominant colors 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 using local and global properties of the image. The robustness of the method is experimentally verified and the color space influence is studied.