Normalised hierarchical data structures for automatic target recognition

A new method is presented that involves teaching an artificial neural network (advanced distributed associative memory ADAM) with a number of synthetic images resulting from a hierarchical data structure descriptor that characterises an object's 3D volume. The method results in a highly accurate recognition process that significantly reduces the duration of a generally time consuming training process. The paper describes a new algorithm for creating the octree data structure of an object, that is based on the theory of volume intersection. The original object is eventually transformed in an abstract synthetic picture that is independent of rotation, translation and scaling and offers a high storage capacity compression rate.<
>