Error Probability in Decision Functions for Character Recognition
- 1 April 1967
- journal article
- Published by Association for Computing Machinery (ACM) in Journal of the ACM
- Vol. 14 (2) , 273-280
- https://doi.org/10.1145/321386.321390
Abstract
Upper bounds for the error probability of a Bayes decision function are derived in terms of the differences among the probability distributions of the features used in character recognition. Applications to feature selection and error reduction are discussed. It is shown that if a sufficient number of well-selected features is used, the error probability can be made arbitrarily small.Keywords
This publication has 3 references indexed in Scilit:
- Optimal Decision Functions for Computer Character RecognitionJournal of the ACM, 1965
- The central limit theorem for dependent random variablesDuke Mathematical Journal, 1948
- Sur l'extension du th or me limite du calcul des probabilit s aux sommes de quantit s d pendantesMathematische Annalen, 1927