Stochastic Model for the Browning-Bledsoe Pattern Recognition Scheme

摘要: A stochastic model is presented which gives the probabilities of successful recognition Browning-Bledsoe scheme as a function parameters and pattern variability parameters. Also, procedures are given for estimating from data so that can be used to predict readability. The adequacy checked by comparing estimated readability with observed two sets data, one high low variability. also treated coding decoding problem in case concepts information theory useful. Finally, brief mention made connection between problems classification general, compared contrasted other schemes make use measurements on patterns.