Connectionist Approach to Transformation Recovery Using Visual Gradient Descent

Abstract

Given an object and a copy of itself produced by an unknown two dimensional affine transformation, a new neural network architecture has been developed that recovers this transformation by minimizing the symmetric difference between the object and the copy. This architecture performs a gradient descent in symmetric difference error space and is designated as visual gradient descent (VGD). The VGD network has applications to both two- and three- dimensional model based automatic target recognition (ATR) and image compression using iterated function systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1991
Accession Number
ADA244703

Entities

People

  • Carey E. Priebe
  • Donald R. Vermillion
  • George W. Rogers
  • Jeffrey L. Solka

Organizations

  • Naval Surface Warfare Center

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Boundaries
  • Classification
  • Computations
  • Image Compression
  • Network Architecture
  • Neural Networks
  • Orientation (Direction)
  • Recognition
  • Recovery
  • Simulations
  • Standards
  • Target Recognition
  • Three Dimensional
  • Translations
  • Two Dimensional
  • Very Large Scale Integration

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Materials Science and Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Space
  • Space - Spacecraft Maneuvers