AUTOMATIC TARGET RECOGNITION USING A NEOCOGNITRON

This paper describes the use of a neocognitron in an automatic target recognition (ATR) system. An image is acquired, edge detected, segmented, and centered on a log-spiral grid using subsystems not discussed in this paper. A conformal transformation is used to map the log-spiral grid to a computation plane in which rotations and scalings are transformed to displacements along the vertical and horizontal axes, respectively. Since the neocognitron can recognize shifted objects, the use of log-spiral images by the neocognitron enables the system to recognize scaled, rotated, and translated objects. Two modifications to prior neocognitron implementations are described. A new weight reinforcement method is introduced which solves a significant training problem for the neocognitron. A method of reducing training time is also introduced which specifies the initial layer of weights in the network. All subsequent layers are trained using unsupervised learning. Simulation results using 32 x 32 and 64 x 64 ICBM images are presented.