Research of metallic and dielectric underground objects on the basis of original computer recognition technique of reflected radio signals

An original recognition technique based on collative classifiers is proposed, enabling the detection and identification of buried objects. This method was previously used for the automatic verification of subscripts. The sequence of classifiers was designed, each of which enables a decision to be made concerning the presence of a given feature in the measured object. The use of different integral features for recognition was investigated. Some experiments were made which showed the possibility of using the proposed method to solve practical problems of object identification.