AN AIDED ADAPTIVE CHARACTER READER FOR MACHINE TRANSLATION OF LANGUAGES,

Abstract

An elementary procedure for the synthesis of a character recognition device based upon a learning experiment is described. Utilizing information derived from a significant sample of the set of characters to be read and given identification of the samples by a human operator, a computer defines a set of 'filters.' These filters may then be used to transform unknown characters having similar type characteristics. During the recognition process a probability matrix for each character in the alphabet is used to compute a figure of merit for the hypothesis that an unknown character is the same as a known character. It is shown that this elementary model might adequately serve for construction of a fast input device for a language translation machine if it were able to make use of frequency distribution characteristics of the dictionary. A possible implementation with a raw character reading rate of up to 500 characters a second appears feasible. (Author)

Document Details

Document Type
Technical Report
Publication Date
May 17, 1960
Accession Number
AD0616666

Entities

People

  • Gerald Estrin
  • Paul Baran

Organizations

  • RAND Corporation

Tags

DTIC Thesaurus Topics

  • Character Recognition
  • Figure Of Merit
  • Identification
  • Language
  • Language Translation
  • Machine Translation
  • Personality
  • Recognition
  • Translations

Readers

  • Approximation Theory.
  • Neural Network Machine Learning.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Translation