The use of neural networks in PSRI target recognition

Abstract
A method for classifying objects invariant to position, rotation, or scale is presented. Objects to be classified were multifunction laser radar data of tanks and trucks at various aspect angles. A segmented Doppler image was used to mask the range image into candidate targets. Each target is then compared to stored templates representing the different classes. The template and the image were transformed into the magnitude of the Fourier transform with log radial and angle axis, the mod F(ln r, theta ) mod position, scale, and rotation invariant (PSRI) feature space. The classification is accomplished using the shape of the correlation peak of the mod F(ln r, theta ) mod planes of an image and a template. A multilayer perceptron neural network using a backpropagation algorithm performs the classification with accuracy near 100%. Results are also presented which yield insight into the problem of selecting the number of hidden nodes for the network.