Invariant Target Recognition Using Self-Organizing Networks

Abstract

This paper presents an overview of neural network technology and specifics of the self-organizing networks. An artificial neural network is described which recognizes objects regardless of their spatial orientation. This network is invariant to rotation, scale, and translation. Invariance is built into the network by introducing a unique set of features which were developed in-house. This overcame the two shortcomings of long training times and combinatorial explosion of terms often present in other networks. Preliminary results suggest that with further refinement and enhancement, the system described in this report will have the capability to reliably recognize targets under adverse environmental conditions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1990
Accession Number
ADA238252

Entities

People

  • Ali Farsaie
  • Beth Farrar
  • J. J. Fuller

Organizations

  • Naval Surface Warfare Center

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Classification
  • Computers
  • Feature Extraction
  • Invariance
  • Neural Networks
  • Orientation (Direction)
  • Recognition
  • Rotation
  • Standards
  • Target Recognition
  • Training
  • Translations
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks