Comparative Analysis of Feature Extraction (2D FFT & Wavelet) and Classification (Lp Metric Distances, MLP NN, & HNet) Algorithms for SAR Imagery

PDF

Authors
  1. Sandirasegaram, N.
  2. English, R.
Corporate Authors
Defence R&D Canada - Ottawa, Ottawa ONT (CAN)
Abstract
The performance of several combinations of feature extraction and target classification algorithms is analyzed for Synthetic Aperture Radar (SAR) imagery using the standard Moving and Stationary Target Acquisition and Recognition (MSTAR) evaluation method. For feature extraction, 2D Fast Fourier Transform (FFT) is used to extract Fourier coefficients (frequency information) while 2D wavelet decomposition is used to extract wavelet coefficients (time-frequency information), from which subsets of characteristic in-class "invariant" coefficients are developed. Confusion matrices and Receiver Operating Characteristic (ROC) curves are used to evaluate and compare combinations of these characteristic coefficients with several classification methods, including Lp, metric distances, a Multi Layer Perceptron (MLP) Neural Network (NN) and AND Corporation's Holographic Neural Technology (HNeT) classifier. The evaluation method examines the trade-off between correct detection rate and false alarm rate for each combination of feature-classifier systems. It also measures correct classification. misclassification and rejection rates for a 90% detection rate. Our analysis demonstrates the importance of feature and classifier selection in accurately classifying new target images.
Keywords
Synthetic Aperture Radar (SAR);Feature extraction;Classification;FFT;Wavelet MLP;HNeT;Neural Network;ROC;Confusion matrix
Report Number
DRDC-OTTAWA-SL-2005-023 — Scientific Literature
Date of publication
01 Mar 2005
Number of Pages
12
Reprinted from
Proceedings of SPIE, vol. 5808, 2005, p 314-325
DSTKIM No
CA027263
CANDIS No
525320
Format(s):
Hardcopy

Permanent link

Document 1 of 1

Date modified: