Nonlinear feature extraction applied to ISAR images of targets for classification

This paper examines the use of a nonlinear dimensionality reduction scheme for feature extraction applied to IS AR images of armoured targets. The features are then used in a nearest-neighbour classifier to evaluate their utility in achieving classification performance that is robust to changes in exterior detail of vehicles (for example open or closed hatches and storage boxes etc.). In addition to robustness a classifier is desired to generalize and correctly classify ail example of a class that was not present in the training process (for example if the training process represents the :Main Battle Tank class with a T72 and a Chieftain. a successful classification is desired when the system is presented with a Challenger). The proportion of the original data structure that has been retained in the dimension reducing transformation is calculated through the use of a loss function. The structure preserving properties of a nonlinear projection using Radial Basis Functions are compared with a linear projection obtained from Principal Components Analysis. The data used are IS AR images of armoured vehicles gathered under a range of vehicle configurations allowing tests of both robustness and generality.