Abstract

Abstracf-The output of a simple statistical categorizer is used to improve recognition performance on a homogeneous data set. An array I $ initial weights contains a coarse description of the various classes; as the system cycles through a set of characters from the same source (a typewritten or printed page), the weights are modified to correspond more closely with the observed distri-butions. The true identities of the characters remain inaccessible throughout the training cycle. This experimental study of the effect of the various parameters in the algorithm is based on ~30 000 characters from fourteen dif-ferent font styles. A fivefold average decrease over the initial rates is obtained in both errors and rejects. HE SELF-CORRECTIVE character recognition T system about to be described differs

Citations