Development And Analysis Of Echo Classification Using Time Delays

The classification of echo waveforms reflected from objects which are composed of multiple scatterers is investigated here. between the multiple echo returns from the individual scattering centers possessed by a reflecting object are investigated as features. generic stochastic point scatterer model is developed for representing the classes of reflecting objects which are of interest. The model allows for uncertainty in the exact relative location of the individual component scatterers. A general optimum Bayesian binary classification decision rule suitable for a large variety of binary classification problems is derived analytically. The classifier decision algorithm is derived for the case when the orientation of the reflecting object is known. Its performance is derived in terms of the probability of error and can be used to bound the performance of a classifier for which the orientation is unknown or must be estimated. Example binary classification problems are presented and analyzed to demonstrate the techniques developed. The time delays