This paper presents an automatic UXO classification system using neural network and fuzzy inference based on the classification rules developed by the OSU. These rules incorporate scattering pattern, polarization and resonance features extracted from an ultra-wide bandwidth, fully polarimetric radar system. These features allow one to discriminate an elongated object. The algorithm consists of two stages. The first-stage classifies objects into clutter (group-A and D), a horizontal linear object (group-B) and a vertical linear object (group-C) according to the spatial distribution of the Estimated Linear Factor (ELF) values. Then second-stage discriminates UXO-LIKE targets from clutters under groups B and C. The rule in the first-stage was implemented by neural network and rules in the second-stage were realized by fuzzy inference with quantitative variables, i.e. ELF level, flatness of Estimated Target Orientation (ETO), the consistency of the target orientation, and the magnitude of the target response. It was found that the classification performance of this automatic algorithm is comparable with or superior to that obtained from a trained expert. However, the automatic classification procedure does not require the involvement of the operator and assigns a unbiased quantitative confidence level (or quality factor) associated with each classification. Classification error and inconsistency associated with fatigue, memory fading or complex features should be greatly reduced.