Extraction of semantic objects from still images

Abstract

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 [1], simplification of the segmentation via region merging, computation of the perceptual metric based on [2] and construction of the structure that represents the image (the binary partition tree [3]).