One-class classifiers and their application to synthetic aperture radar target recognition.

摘要

Target recognition requires the ability to distinguish targets from non-targets, a capability called one-class generalization. To function as a one-class classifier, a neural network must have three types of generalization: within-class, between-class, and out-of-class. We discuss these three types of generalization and identify neural network architectures that meet these requirements. We have applied our one-class classifier ideas to the problem of automatic target recognition in synthetic aperture radar. We have compared three neural network algorithms: Carpenter and Grossberg's algorithmic version of the Adaptive Resonance Theory (ART-2A), Kohonen's Learning Vector Quantization (LVQ), and Reilly and Cooper's Restricted Columb Energy network (RCE). The ART 2-A neural network has given the best results, with 100% within-class, and out-of-class generalization. Experiments show that the network's performance is sensitive to vigilance and number of training set presentations.