A set of neural lattices that use the central limit for Fourier and Gabor transforms, multiple-scale Gaussian smoothing, and edge detection

Author

Ben-Arie, Jezekiel

Author_Institution

Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA

fYear

1991

fDate

14-17 May 1991

Firstpage

537

Abstract

A set of neural lattices based on the central limit theorem is described. Each of the described lattices generates in parallel a set of multiscale Gaussian smoothings of their input arrays. The recursive smoothing principle of the lattices can be extended to any dimension. In addition, the lattices can generate a variety of multiple-scale operators such as the edge detectors of J. Canny (1986), Laplacians of Gaussians, and multidimensional Fourier and Gabor transforms

Keywords

Fourier transforms; Laplace transforms; image processing; neural nets; pattern recognition; signal processing; Gabor transforms; central limit theorem; edge detection; input arrays; multidimensional Fourier transforms; multilayered lattice structure; multiple-scale Gaussian smoothing; neural lattices; recursive smoothing principle; Convolution; Detectors; Fourier transforms; Gaussian processes; Image edge detection; Laplace equations; Lattices; Neural networks; Smoothing methods; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1991., Proceedings of the 34th Midwest Symposium on

Conference_Location

Monterey, CA

Print_ISBN

0-7803-0620-1

Type

conf

DOI

10.1109/MWSCAS.1991.252105

Filename

252105