High-fidelity image interpolation using radial basis function neural networks

Author

Ahmed, Farid ; Gustafson, Steve C. ; Karim, M.A.

Author_Institution

Dayton Univ., OH, USA

Volume

2

fYear

1995

fDate

22-26 May 1995

Firstpage

588

Abstract

Image interpolation using radial basis function (RBF) neural networks is accomplished. In this work the RBF network is first trained with the given image, satisfying the constraint of the gray value at each pixel. With the desired magnification ratio, each pixel is then divided into subpixels. The subpixel gray values are calculated using the trained network. Two dimensional Gaussian basis functions are used as the neurons in the hidden layer

Keywords

Gaussian distribution; feedforward neural nets; image enhancement; image resolution; interpolation; rendering (computer graphics); smoothing methods; 2D Gaussian basis functions; adaptive scheme; edge preservation; enhanced image; gray value; hidden layer neurons; high-fidelity image interpolation; image fidelity; image smoothness; radial basis function neural networks; receptive field width; rendering; simulation; subpixels; trained network; Computed tomography; Degradation; Feeds; Gaussian processes; Interpolation; Neural networks; Neurons; Radial basis function networks; Spline; Tiles;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, 1995. NAECON 1995., Proceedings of the IEEE 1995 National

Conference_Location

Dayton, OH

ISSN

0547-3578

Print_ISBN

0-7803-2666-0

Type

conf

DOI

10.1109/NAECON.1995.521997

Filename

521997