Handwritten Character Recognition Using Feature Extraction and Neural Networks

Abstract

A novel set of affine invariant features and an accompanying neural network are described for performing two-dimensional pattern recognition. The features are described and shown to be affine invariant. The validity of the approach and the need for a neural network are demonstrated by applying the features and the network model to handwritten character recognition.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 12, 1991
Accession Number
ADA238294

Entities

People

  • A. Farsaie
  • J. J. Fuller
  • T. Dumoulin

Organizations

  • Naval Surface Warfare Center

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Character Recognition
  • Classification
  • Extraction
  • Feature Extraction
  • Identification
  • Neural Networks
  • Pattern Recognition
  • Personality
  • Recognition
  • Surface Warfare
  • Target Recognition
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks