Automatic ship classification using support vector machines

Authors:
B. Owen;M. Palanisami;L. Swierkowski
Affiliations:
Centre of Expertise in Networked Decisions & Sensor Systems, Department of Electrical and Electronic Engineering, University of Melbourne, Vic.;Centre of Expertise in Networked Decisions & Sensor Systems, Department of Electrical and Electronic Engineering, University of Melbourne, Vic.;Weapons Systems Division, DSTO, PO Box 1500 Edinburgh, South Australia
Venue:
Design and application of hybrid intelligent systems
Year:
2003

Citing 5
Cited 0

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Automatic Capacity Tuning of Very Large VC-Dimension Classifiers

Advances in Neural Information Processing Systems 5, [NIPS Conference]

Quantified Score

Hi-index	0.00

Visualization

Abstract

Inferred (IR) ship images can be noisy, blurry and small making classification difficult. A SVM classification system for IR ship images was investigated. Mathematically modeling the scene of interest was performed with the aim of mapping the 2D image back into the 3D scene. The mathematical model is used to obtain more accurate estimates of the feature vectors. Part of the mathematical model requires the estimation of the position of the horizon in the IR image. Three different SVM based classifiers were evaluated using real IR images of ships.