Extraction of semantic objects from still images

In this work, we study the extraction of semantic objects from still images. We combine different ideas to extract them in a structured manner together with a perceptual metric that ranks them according with its perceptual relevance. The algorithm has four steps, the regularization of the initial segmentation using probability diffusion, simplification of the segmentation via region merging, computation of the perceptual metric and construction of the structure that represents the image (the binary partition tree).