IDENTIFICATION AND DIFFERENTIATION OF HANDWRITINGS WITH THE HELP OF ELECTRONIC COMPUTERS (OPOZANIE I DIFFERENTSYATSIYA POCHERKOV PRI POMOSHCHI ELEKTRONNOVYCHISLITELNYKH MASHIN),

Abstract

The general problem of machine recognition and discrimination of handwriting, the development of the necessary algorithms, and the theoretical principles underlying the process of teaching an automation handwriting analysis are discussed. The discussion is based parimarily on certain theoretical work in this area that has been carried out at the VTs LGU. A detailed explanation is given of the manner in which the handwriting or 'graphic' material is converted into a system of numbers suitable for computer processing, and several different metrization techniques are described. The principle of the 'dynamic stereotype of writing' (a fundamental assumption of the method proposed) is introduced as a means of neutralizing random or deliberate handwriting deviations from an established and quantized standard. The necessary and sufficient conditions for the validity of this hypothesis are stated. Examples are given and an analysis is made of the results of certain machine experiments using the general techniques outlined. The theoretical considerations and experiments described substantiate the possibility in principle of employing computers for the differentiation of similar handwriting styles. (Author)

Document Details

Document Type
Technical Report
Publication Date
Sep 14, 1967
Accession Number
AD0670075

Entities

People

  • B. M. Sokolov
  • B. N. Kozinets
  • R. M. Lantsman
  • V. A. Yakubovich

Organizations

  • National Air and Space Intelligence Center

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Automation
  • Computers
  • Discrimination
  • Handwriting
  • Identification
  • Materials
  • Recognition
  • Standards
  • Writing

Readers

  • Computer Science.
  • Speech Processing/Speech Recognition.
  • Theoretical Analysis.

Technology Areas

  • Microelectronics