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

M Everingham; HL Muller; B Thomas

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

M Everingham, HL Muller, B Thomas

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 contribution	Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space
Original language	English
Title of host publication	Unknown
Editors	Tim Cootes, Chris Taylor
Publisher	BMVA
Pages	363 - 372
Number of pages	9
Publication status	Published - Sept 2001

Bibliographical note

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

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000544

Handle.net

Persistent link

Cite this

@inproceedings{d67f2bfb7c294729a169baf1f38b0073,

title = "Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space",

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.",

author = "M Everingham and HL Muller and B Thomas",

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

year = "2001",

month = sep,

language = "English",

pages = "363 -- 372",

editor = "Tim Cootes and Chris Taylor",

booktitle = "Unknown",

publisher = "BMVA",

}

TY - GEN

T1 - Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space

AU - Everingham, M

AU - Muller, HL

AU - Thomas, B

N1 - Conference Proceedings/Title of Journal: Proceedings of the 12th British Machine Vision Conference (BMVC2001)

PY - 2001/9

Y1 - 2001/9

N2 - 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.

AB - 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.

M3 - Conference Contribution (Conference Proceeding)

SP - 363

EP - 372

BT - Unknown

A2 - Cootes, Tim

A2 - Taylor, Chris

PB - BMVA

ER -

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

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this