Connectionist Approach to Transformation Recovery Using Visual Gradient Descent
NAVAL SURFACE WARFARE CENTER DAHLGREN VA
Pagination or Media Count:
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.
- Computer Programming and Software
- Computer Systems