Share Email Print

Proceedings Paper

Evaluation of SVM classification of metallic objects based on a magnetic-dipole representation
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In the electromagnetic-induction (EMI) detection and discrimination of unexploded ordnance (UXO) it is important for inversion purposes to have an efficient forward model of the detector-target interaction. Here we revisit an attractively simple model for EMI response of a metallic object, namely a hypothetical anisotropic, infinitesimal magnetic dipole characterized by its magnetic polarizability tensor, and investigate the extent to which one can train a Support Vector Machine (SVM) to produce reliable gross characterization of objects based on the inferred tensor elements as discriminators. We obtain the frequency-dependent polarizability tensor elements for various object characteristics by using analytical solutions to the EMI equations. Then, using synthetic data and focusing on gross shape and especially size, we evaluate the classification success of different SVM formulations for different kinds of objects.

Paper Details

Date Published: 16 May 2006
PDF: 8 pages
Proc. SPIE 6217, Detection and Remediation Technologies for Mines and Minelike Targets XI, 621703 (16 May 2006); doi: 10.1117/12.667963
Show Author Affiliations
Juan Pablo Fernández, Dartmouth College (United States)
Benjamin Barrowes, U.S. Army Corps of Engineers (United States)
Kevin O'Neill, Dartmouth College (United States)
U.S. Army Corps of Engineers (United States)
Keith Paulsen, Dartmouth College (United States)
Irma Shamatava, Dartmouth College (United States)
Fridon Shubitidze, Dartmouth College (United States)
Keli Sun, Dartmouth College (United States)

Published in SPIE Proceedings Vol. 6217:
Detection and Remediation Technologies for Mines and Minelike Targets XI
J. Thomas Broach; Russell S. Harmon; John H. Holloway Jr., Editor(s)

© SPIE. Terms of Use
Back to Top