Bayesian Point Set Matching of Scattering Featureswithapplication to Object Recognition

We present a statistical decision approach for the point set matching of unordered feature sets. Both feature sets have associated uncertainties, and the number of elements in each set may be different. Computation of the match likelihood requires a correspondence between feature sets; we solve the correspondence problem in polynomial time using the Hungarian algorithm. We also consider the problem of matching when there is an unknown translation between the point sets. We present Bayes match solutions for both the deterministic and the random translation cases. Finally, we apply this matching method to the problem of synthetic aperture radar target classification from scattering center feature sets.