The effect of the surface roughness to the classification of buried cylindrical targets

The electric field scattered from the buried cylindrical target is calculated by using Equivalence Principle and Moment Method, and the database is formed by using the scattered fields from three cylindrical targets at certain frequencies. Radial Basis Function Network is proposed for target classification. A portion of the database is used to train the network and the rest is used to test the performance of the neural network. This target classification process has been repeated by changing the surface roughness of the medium, in which is the target buried, and effects of the surface roughness to the target classification are investigated.