27 August 1993 Satellite image processing using a hammering neural network
Author Affiliations +
Abstract
It is shown that images with missing pixels can be approximately and usefully reconstructed using an interpolation function derived from as few as 10% of the original pixels in the image. The interpolation procedure uses Gaussian radial basis functions to `hammer' a plane to the given data points, where the basis function widths are calculated according to diagonal dominance criteria. In this paper the effectiveness of the reconstruction technique is investigated as a function of the degree of diagonal dominance.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David W. Gilbert, David W. Gilbert, Steven C. Gustafson, Steven C. Gustafson, } "Satellite image processing using a hammering neural network", Proc. SPIE 1961, Visual Information Processing II, (27 August 1993); doi: 10.1117/12.150949; https://doi.org/10.1117/12.150949
PROCEEDINGS
14 PAGES


SHARE
RELATED CONTENT

Hybrid road recognition method using fuzzy c means and back...
Proceedings of SPIE (September 24 2003)
Quality improvement of Beijing-1 small satellite images
Proceedings of SPIE (November 23 2008)
Inhomogeneous cloud removing from remote sensing image
Proceedings of SPIE (November 23 2011)
SPOT5 system
Proceedings of SPIE (September 23 1999)

Back to Top