Cueing, feature discovery, and one-class learning for synthetic aperture radar automatic target recognition

• Published in: Neural networks Vol. 8; no. 7; pp. 1081 - 1102
• Main Authors: Koch, Mark W., Moya, Mary M., Hostetler, Larry D., Fogler, R.Joseph
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.01.1995; Elsevier Science
• Subjects: Applied sciences; Automatic target recognition; Cueing using focus-of-attention; Exact sciences and technology; Feature discovery using Neocognitron and generalized Hebbian algorithm; Information, signal and communications theory; One-class classification using adaptive resonance theory (ART 2-A); Partial obscuration recognition using hyperstar metric; Pattern recognition; Signal processing; Synthetic aperture radar; Telecommunications and information theory; Partial obscuration recognition using hyperstar metric; Feature discovery using Neocognitron and generalized Hebbian algorithm; Automatic target recognition; Cueing using focus-of-attention; One-class classification using adaptive resonance theory (ART 2-A); Synthetic aperture radar; Learning; Modular architecture; Identification; Pattern recognition; Neural network; Automatic recognition; Pattern extraction
• DOI: 10.1016/0893-6080(95)00049-6
• ISSN: 0893-6080

The exquisite capabilities of biological neural systems for recognizing target patterns subject to large variations have motivated us to investigate neurophysiologically-inspired techniques for automatic target recognition. This paper describes a modular multi-stage architecture for focus-of-attention cueing, feature discovery and extraction, and one-class pattern learning and identification in synthetic aperture radar imagery. To prescreen massive amounts of image data, we apply a focus-of-attention algorithm using data skewness to extract man-made objects from natural clutter regions. We apply self-organizing feature discovery algorithms that uniquely characterize targets in a reduced dimension space and use self-organizing one-class classifiers for learning target variations. We also develop a distance metric for partial obscuration recognition. We present performance results using simulated SAR data and test for within-class generalization using nontrained targets including both in-the-clear and partially obscured examples. We test for between-class generalization using non-trained targets including both in-the-clear and partially obscured examples. We test for between-class generalization using near-target data.