Design of a neural network character recognizer for a touch terminal

I. Guyon, P. Albrecht, Y. Le Cun, J. Denker, W. Hubbard

Research output: Contribution to journalArticlepeer-review

Abstract

We describe a system which can recognize digits and uppercase letters handprinted on a touch terminal. A character is input as a sequence of [x(t), y(t)] coordinates, subjected to very simple preprocessing, and then classified by a trainable neural network. The classifier is analogous to "time delay neural networks" previously applied to speech recognition. The network was trained on a set of 12,000 digits and uppercase letters, from approximately 250 different writers, and tested on 2500 such characters from other writers. Classification accuracy exceeded 96% on the test examples.

Original languageEnglish (US)
Pages (from-to)105-119
Number of pages15
JournalPattern Recognition
Volume24
Issue number2
DOIs
StatePublished - 1991

Keywords

  • Character recognition
  • Handwritten characters
  • Neural networks
  • On-line character recognition
  • Touch screen
  • Touch terminal

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Design of a neural network character recognizer for a touch terminal'. Together they form a unique fingerprint.

Cite this