Accession Number:

ADA355591

Title:

Stable Feature Extraction in Aerial Reconnaissance Images

Descriptive Note:

Final technical rept. 15 Aug 92-12 Aug 96

Corporate Author:

KENTUCKY UNIV RESEARCH FOUNDATION LEXINGTON

Personal Author(s):

• Chenoweth, Darrel L.

Report Date:

1998-06-01

Pagination or Media Count:

376.0

Abstract:

The problem of extracting stable features in aerial reconnaissance images is addressed in this report. Fractal models of image features are proposed an concept of fractal error is introduced. Fractal error is a metric that quantifies the closeness of fit of the image feature to a fractal model. Using this metric one can discriminate between natural and man-made features in an image. Fractal error also presents a useful approach to extracting edges in images. Methods are given for computing and approximating fractal error using networks and genetic algorithms.

Descriptors:

• *PATTERN RECOGNITION
• *FEATURE EXTRACTION
• ALGORITHMS
• FRACTALS
• AERIAL RECONNAISSANCE
• RULE BASED SYSTEMS
• SYNTHETIC APERTURE RADAR
• RADAR IMAGES
• MILITARY APPLICATIONS
• AERIAL PHOTOGRAPHY

Subject Categories:

• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE