Share Email Print

Optical Engineering

Wavelet-based fractal signature analysis for automatic target recognition
Author(s): Fausto Espinal; Terrance L. Huntsberger; Bjorn D. Jawerth; Toshiro Kubota
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Texture measures offer a means of detecting targets in background clutter that has similar spectral characteristics. Our previous studies demonstrated that the ‘‘fractal signature’’ (a feature set based on the fractal surface area function) is very accurate and robust for grayscale texture classification. This paper introduces a new multichannel texture model that characterizes patterns as 2-D functions in a Besov space. The wavelet-based fractal signature generates an n-dimensional surface, which is used for classification. Results of some experimental studies are presented demonstrating the usefulness of this texture measure.

Paper Details

Date Published: 1 January 1998
PDF: 9 pages
Opt. Eng. 37(1) doi: 10.1117/1.601844
Published in: Optical Engineering Volume 37, Issue 1
Show Author Affiliations
Fausto Espinal, Univ. of South Carolina (United States)
Terrance L. Huntsberger, Univ. of South Carolina (United States)
Bjorn D. Jawerth, Univ. of South Carolina (United States)
Toshiro Kubota, Georgia Institute of Technology (United States)

© SPIE. Terms of Use
Back to Top