Cerca risorse accademiche

This paper presents a database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations ...

A general non-parametric technique is proposed for the analysis of a complex multimodal feature space and to delineate arbitrarily shaped clusters in it. The basic computational module of the technique is an old pattern ...

In this work we study the extraction of semantic objects from images together with a metric that ranks them according to their perceptual significance. To obtain an initial segmentation we use elements of mathematical mo...