Image segmentation by region growing and spectral clustering with a natural convergence criterion

Author

Tilton, James C.

Author_Institution

NASA Goddard Space Flight Center, Greenbelt, MD, USA

Volume

4

fYear

1998

fDate

6-10 Jul 1998

Firstpage

1766

Abstract

The image segmentation approach described is a new hybrid of region growing and spectral clustering. This approach produces a specified number of hierarchical segmentations at different levels of detail, based upon jumps in a dissimilarity criterion. A recursive implementation of this segmentation approach on a cluster of 66 Pentium Pro PCs is described, and the effectiveness of this segmentation approach on Landsat Multispectral Scanner data is discussed

Keywords

geophysical signal processing; geophysical techniques; image segmentation; remote sensing; Landsat; dissimilarity criterion; geophysical measurement technique; hierarchical segmentation; image region growing; image segmentation; land surface; multispectral remote sensing; natural convergence criterion; recursive implementation; spectral clustering; terrain mapping; Convergence; Facsimile; Image segmentation; Labeling; Personal communication networks; Postal services; Process control; Remote sensing; Satellites; Telephony;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium Proceedings, 1998. IGARSS '98. 1998 IEEE International

Conference_Location

Seattle, WA

Print_ISBN

0-7803-4403-0

Type

conf

DOI

10.1109/IGARSS.1998.703645

Filename

703645