Published September 29, 1985
| public
Journal Article
Computational vision and regularization theory
- Creators
- Poggio, Tomaso
- Torre, Vincent
-
Koch, Christof
Abstract
Descriptions of physical properties of visible surfaces, such as their distance and the presence of edges, must be recovered from the primary image data. Computational vision aims to understand how such descriptions can be obtained from inherently ambiguous and noisy data. A recent development in this field sees early vision as a set of ill-posed problems, which can be solved by the use of regularization methods. These lead to algorithms and parallel analog circuits that can solve 'ill-posed problems' and which are suggestive of neural equivalents in the brain.
Additional Information
© 1985 Nature Publishing Group. We thank E. Hildreth, A. Hurlbert, J. Marroquin, G. Mitchison, D. Terzopoulos, H. Voorhees and A. Yuille for discussions and suggestions. Mario Bertero first pointed out to us that numerical differentiation is an ill-posed problem. E. Hildreth, L. Ardrey and especially H. Voorhees, K. Sims and M. Drumheller helped with some of the figures. Support for the Artificial Intelligence Laboratory's research in artificial intelligence 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. The Center for Biological Information Processing is supported in part by the Sloan Foundation and in part by Whitaker College. C.K. is supported by a grant from the Office of Naval Research, Engineering Psychology Division.Additional details
- Eprint ID
- 40492
- DOI
- 10.1038/317314a0
- Resolver ID
- CaltechAUTHORS:20130816-103220770
- N00014-80-C-0505
- Office of Naval Research (ONR)
- Alfred P. Sloan Foundation
- Whitaker College
- Advanced Research Projects Agency (ARPA)
- Created
-
2008-01-26Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field
- Caltech groups
- Koch Laboratory (KLAB)