Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space

M Everingham, HL Muller, B Thomas

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

Image segmentation is the first stage of processing in many practical computer vision systems. While development of particular segmentation algorithms has attracted considerable research interest, relatively little work has been published on the subject of their evaluation. In this paper we propose a framework for quantitative evaluation of segmentation algorithms which we believe addresses shortcomings of previous approaches, and use this framework to compare several state-of-the-art algorithms.
Translated title of the contributionEvaluating image segmentation algorithms using monotonic hulls in fitness/cost space
Original languageEnglish
Title of host publicationUnknown
EditorsTim Cootes, Chris Taylor
PublisherBMVA
Pages363 - 372
Number of pages9
Publication statusPublished - Sep 2001

Bibliographical note

Conference Proceedings/Title of Journal: Proceedings of the 12th British Machine Vision Conference (BMVC2001)

Fingerprint

Dive into the research topics of 'Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space'. Together they form a unique fingerprint.

Cite this