Segmentation of color images using a hierarchical fuzzy region merging technique

A novel hierarchical clustering method is presented in this work. It operates as a part of a split and merge segmentation scheme. The proposed technique incorporates the use of several color features to compare clusters in the RGB space and the flexibility of the fuzzy reasoning approach to accomplish satisfactory segmentation results. The boundary values of the fuzzy sets have been determined by means of a genetic algorithm optimization approach. The segmentation results evaluated subjectively and objectively were compared to a straightforward product cost function.