Target classification performance as a function of measurement uncertainty

In this paper, we demonstrate target classification using the proposed features in previously reported research under measurement uncertainty conditions. The MSTAR dataset is widely used real target measurements in automatic target recognition society. Extremely high classification results of the dataset, which are over 90% correct classification, have been reported from some literatures. However, this high classification results could be acquired not only by the classification system, but also the cleanness of the dataset. Therefore, in this paper, more realistic target classification scenarios including target aspect angle estimation error, strong white Gaussian noise, and different combination of test and training targets are applied for classification and its corresponding results are examined. The proposed target feature extraction techniques show the robustness of the measurement uncertainties and excellent classification results.