Abstract.
We describe a neural network that enhances and completes salient closed contours in images. Our work is different from all previous work in three important ways. First, like the input provided to primary visual cortex (V1) by the lateral geniculate nucleus (LGN), the input to our computation is isotropic. That is, it is composed of spots, not edges. Second, our network computes a well-defined function of the input based on a distribution of closed contours characterized by a random process. Third, even though our computation is implemented in a discrete network, its output is invariant to continuous rotations and translations of the input image.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received: 11 July 2002 / Accepted in revised form: 25 October 2002
Acknowledgements. L.R.W. was supported in part by Los Alamos National Laboratory. J.W.Z. was supported in part by the Albuquerque High Performance Computing Center. We wish to thank Jonas August and Steve Zucker for their insightful comments.
Correspondence to: L.R. Williams (e-mail: Williams@cs.unm.edu)
Rights and permissions
About this article
Cite this article
Williams, L., Zweck, J. A rotation and translation invariant discrete saliency network. Biol. Cybern. 88, 2–10 (2003). https://doi.org/10.1007/s00422-002-0370-x
Issue Date:
DOI: https://doi.org/10.1007/s00422-002-0370-x