CaltechAUTHORS
  A Caltech Library Service

Analog "neuronal" networks in early vision

Koch, Christof and Marroquin, Jose and Yuille, Alan (1986) Analog "neuronal" networks in early vision. Proceedings of the National Academy of Sciences of the United States of America, 83 (12). pp. 4263-4267. ISSN 0027-8424. http://resolver.caltech.edu/CaltechAUTHORS:KOCpnas86

[img]
Preview
PDF - Published Version
See Usage Policy.

1176Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:KOCpnas86

Abstract

Many problems in early vision can be formulated in terms of minimizing a cost function. Examples are shape from shading, edge detection, motion analysis, structure from motion, and surface interpolation. As shown by Poggio and Koch [Poggio, T. & Koch, C. (1985) Proc. R. Soc. London, Ser. B 226, 303-323], quadratic variational problems, an important subset of early vision tasks, can be "solved" by linear, analog electrical, or chemical networks. However, in the presence of discontinuities, the cost function is nonquadratic, raising the question of designing efficient algorithms for computing the optimal solution. Recently, Hopfield and Tank [Hopfield, J. J. & Tank, D. W. (1985) Biol. Cybern. 52, 141-152] have shown that networks of nonlinear analog "neurons" can be effective in computing the solution of optimization problems. We show how these networks can be generalized to solve the nonconvex energy functionals of early vision. We illustrate this approach by implementing a specific analog network, solving the problem of reconstructing a smooth surface from sparse data while preserving its discontinuities. These results suggest a novel computational strategy for solving early vision problems in both biological and real-time artificial vision systems.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://www.pnas.org/content/83/12/4263.abstract?sid=bd350e12-da10-49f8-a938-0d34cb4fae7cPublisherArticle
Additional Information:© 1986 by the National Academy of Sciences. Communicated by John J. Hopfield, January 27, 1986. We thank John Hopfield, Francis Crick, Tom Knight, Carver Mead, Tomaso Poggio, Eric Saund, and Demitri Terzopoulos for many useful discussions and suggestions. The Center's support is provided in part by the Sloan Foundation and in part by Whitaker College. Support for the Artificial Intelligence Laboratory's research is provided in part by the Advanced Research Projects Agency of the Department of Defense under Office of Naval Research Contract N00014-80-C-0505. J.M. is supported by the Army Research Office under contract ARO-DAAG29-84-K-0005. C.K. is supported by a grant from the Office of Naval Research, Engineering Psychology Division to Tomaso Poggio. The publication costs of this article were defrayed in part by page charge payment. This article must therefore be hereby marked "advertisement" in accordance with 18 U.S.C. §1734 solely to indicate this fact.
Group:Koch Laboratory, KLAB
Subject Keywords:surface reconstruction; motion segmentation; analog hardware; parallel computing
Record Number:CaltechAUTHORS:KOCpnas86
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:KOCpnas86
Alternative URL:http://dx.doi.org/10.1073/pnas.83.12.4263
Official Citation: C Koch, J Marroquin, and A Yuille Analog "neuronal" networks in early vision PNAS 1986 83 (12) 4263-4267
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:7682
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:22 Mar 2007
Last Modified:19 Sep 2013 21:46

Repository Staff Only: item control page