A fast learning algorithm for Gabor transform with applications to image data reduction and pattern classification

Author

Ibrahim, Ayman E. ; Sadjadi, Mahmood R Azimi ; Sheedvash, Sassan

Author_Institution

Dept. of Electr. Eng., Colorado State Univ., Fort Collins, CO, USA

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4321

Abstract

A simple neural network-based approach is introduced, which allows the computation of the coefficients of the generalized non-orthogonal 2D Gabor transform representation. The network is trained using a recursive least squares (RLS) type algorithm. This RLS learning algorithm offers better accuracy and faster convergence when compared to the least mean squares based algorithms. The aim is to achieve minimum mean squared error for the reconstructed image from the set of the Gabor coefficients. Applications of this scheme in image data reduction and pattern classification are demonstrated in the simulation results

Keywords

data reduction; image classification; image reconstruction; learning (artificial intelligence); least squares approximations; neural nets; transforms; Gabor coefficients; Gabor transform; convergence; fast learning algorithm; image data reduction; image reconstruction; minimum mean squared error; neural network; pattern classification; recursive least squares learning; Convergence; Data compression; Fourier transforms; Frequency; Image reconstruction; Least squares approximation; Least squares methods; Neural networks; Pattern classification; Resonance light scattering;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374962

Filename

374962