Image processing operators and transforms generated by a set of multidimensional neural lattices that use the central limit

Author

Ben-Arie, Jezekiel

Author_Institution

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

fYear

1991

fDate

18-21 Nov 1991

Firstpage

987

Abstract

A set of neural lattices based on the central limit theorem is described. Each of the lattices generates in parallel a set of multiple scale 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 Canny´s edge detectors, Laplacians of Gaussians, and multi-dimensional Fourier and Gabor transforms

Keywords

computerised pattern recognition; computerised picture processing; neural nets; transforms; Canny´s edge detectors; Laplacians of Gaussians; central limit theorem; computerised pattern recognition; computerised picture processing; image processing operators; multidimensional Fourier transforms; multidimensional Gabor transforms; multidimensional neural lattices; multiple scale Gaussian smoothings; multiple scale operators; neural nets; recursive smoothing principle; Convolution; Detectors; Fourier transforms; Image edge detection; Image processing; Laplace equations; Lattices; Multidimensional systems; Smoothing methods; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1991. 1991 IEEE International Joint Conference on

Print_ISBN

0-7803-0227-3

Type

conf

DOI

10.1109/IJCNN.1991.170589

Filename

170589