OPTIMUM CLASSIFICATION OF CORRELATION-PLANE DATA BY BAYESIAN DECISION-THEORY

A multimodal model for correlation-plane distributions generated by co mposite filters is presented. From this model a statistical classifier referred to as a composite Bayesian classifier is developed. By explo iting the Gaussian behavior of correlation-plane data, this classifier concisely represents multimodal distributions as composite algebraic functions. These multimodal distributions, each of which is constructe d by superposition of many normal distributions, are used to partition a vector signal space into optimum classification regions derived fro m Bayes's likelihood ratio test. For the purpose of validating the mul timodal model, expected performance for the training images is derived from calibration data and compared with observed performance.