Automatic target recognition using image and network decomposition
P.Y. Mundkur, U.B. Desai · 1991
A constrained version of the general automatic target recognition problem is formulated in the context of pattern recognition, as the detection and localization of target patterns in scene images. An approach to the simplification of the learning involved is presented. The two-stage network architecture that results from this approach incorporates two cascaded modules: a multilayered perceptron followed by a modified Maxnet. The network provides translation-invariant recognition of targets. Simulation results are presented.>