Region-based segmentation of color images: application to aerial image cartography

Author

Devaux, J.C. ; Kouassi, R.K. ; Gouton, P. ; Truchetet, F.

Author_Institution

Lab. d´´Electronique, d´´Inf. et d´´Image, Bourgogne Univ., Dijon, France

Volume

2

fYear

1997

fDate

2-5 Nov. 1997

Firstpage

1735

Abstract

A process for performing cartography of aerial color images by region-based segmentation is presented. Such cartographies are desired, for example, in ecological applications. Previous works have shown that edge detection is not satisfactory for cartography. The efficiency of the region-based approaches is discussed in a comparative study between various methods which are commonly used in image analysis. The comparison is performed in terms of a dissimilarity measure.

Keywords

agriculture; cartography; ecology; image classification; image colour analysis; image representation; image segmentation; aerial color images; aerial image cartography; automatic mapping; classification algorithm; color CCD camera; color representation; dissimilarity measure; ecological applications; edge detection; image analysis; region-based segmentation; vegetable population; Charge coupled devices; Hardware; Image color analysis; Image edge detection; Image resolution; Image segmentation; Performance evaluation; Satellites; Spatial resolution; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems & Computers, 1997. Conference Record of the Thirty-First Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-8316-3

Type

conf

DOI

10.1109/ACSSC.1997.679199

Filename

679199