CLASSIFIER AND SHIFT-INVARIANT AUTOMATIC TARGET RECOGNITION NEURAL NETWORKS

Automatic target recognition processors typically employ several stage s of processing, each with a different operational purpose. New shift- invariant filters using morphological and Gabor wavelet transform oper ations are described for use in the initial stages of such a system. T heir realization on simple correlation neural networks are noted, toge ther with the use of neural net optimization techniques to design such filters. A new feature space trajectory classifier neural network is described that identifies the class and pose of each object, rejects c lutter false alarms, and overcomes various issues associated with othe r classifier neural networks.