 |
 |
 |
 |
|
| back | ||||
Abstract
Feature Extraction Using Spatial Context
Track: Remote Sensing Imagery
Author(s): David Opitz
When classifying the contents of imagery, there are only a few attributes accessible to human interpreters. For any single set of imagery these are shape, size, color, texture, pattern, shadow, and association. Traditional image processing techniques incorporate only color (spectral signature) and perhaps texture or pattern into an involved expert work flow process. This is why these techniques typically fail when populating GIS databases. This paper shows a successful machine learning method for integrating spatial context into the feature extraction process, thus leveraging the remaining attributes of shape, size, shadow, and association. Results demonstrate the utility of this approach.
David Opitz
University of Montana
Computer Science Department
Social Science Building
Missoula , MT 59812
USA
Phone: 406-243-2831
Fax: 406-243-5139
E-mail: opitz@cs.umt.edu