Skip to main content
BOUNDARY EXTRACTION IN NATURAL IMAGES USING ULTRAMETRIC CONTOUR MAPS

P. ARBELAEZ

PROCEEDINGS 5TH IEEE WORKSHOP ON PERCEPTUAL ORGANIZATION IN COMPUTER VISION (POCV’06). JUNE 2006. NEW YORK, USA

Abstract

This paper presents a low-level system for boundary extraction and segmentation of natural images and the evaluation of its performance. We study the problem in the framework of hierarchical classification, where the geometric structure of an image can be represented by an ultrametric contour map, the soft boundary image associated to a family of nested segmentations. We define generic ultrametric distances by integrating local contour cues along the regions boundaries and combining this information with region attributes. Then, we evaluate quantitatively our results with respect to ground-truth segmentation data, proving that our system outperforms significantly two widely used hierarchical segmentation techniques, as well as the state of the art in local edge detection.