Automatic marker generation for watershed segmentation of natural images

Automatic marker selection for watershed segmentation is a difficult problem. Most of the existing procedures are intended for specific application fields and usually require some prior knowledge about the problem at hand. A simple and general method for generating markers is proposed. The markers are obtained from the splitting of the three-dimensional (3D) colour histogram of the image and imposed as minima for watershed segmentation. The method has been tested on natural images from the Berkeley segmentation dataset (BSDS500), showing results comparable with the state-of-the-art segmentation algorithms.