Graph based smoothing and segmentation of color images

This paper presents a simplification and merging technique based on an initial region partition of color images: a region adjacency graph (RAG). We propose a general scheme that can be employed for both color image simplification and/or segmentation. A new filtering algorithm of RAG is presented and included within a merging algorithm. The region models associated to each node are simplified and moreover the RAG is simplified by merging similar nodes.