Computational vision and regularization theory
- 1 September 1985
- journal article
- review article
- Published by Springer Nature in Nature
- Vol. 317 (6035) , 314-319
- https://doi.org/10.1038/317314a0
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.Keywords
This publication has 28 references indexed in Scilit:
- Computer Vision and Natural ConstraintsScience, 1984
- Parallel visual computationNature, 1983
- Multilevel computational processes for visual surface reconstructionComputer Vision, Graphics, and Image Processing, 1983
- A computational theory of visual surface interpolationPhilosophical Transactions of the Royal Society of London. B, Biological Sciences, 1982
- Computational Approaches to Image UnderstandingACM Computing Surveys, 1982
- From Images to SurfacesPublished by MIT Press ,1981
- Numerical shape from shading and occluding boundariesArtificial Intelligence, 1981
- Determining optical flowArtificial Intelligence, 1981
- Interpreting line drawings as three-dimensional surfacesArtificial Intelligence, 1981
- Determining lightness from an imageComputer Graphics and Image Processing, 1974