Accession Number:

ADA244703

Title:

Connectionist Approach to Transformation Recovery Using Visual Gradient Descent

Descriptive Note:

Corporate Author:

NAVAL SURFACE WARFARE CENTER DAHLGREN VA

Report Date:

1991-11-01

Pagination or Media Count:

34.0

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.

Subject Categories:

  • Computer Programming and Software
  • Computer Systems

Distribution Statement:

APPROVED FOR PUBLIC RELEASE