A fast learning algorithm for Gabor transform extraction

Author

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

Author_Institution

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

Volume

3

fYear

1994

fDate

30 May-2 Jun 1994

Firstpage

281

Abstract

A simple neural network-based approach is introduced in this paper which allows the computation of the coefficients of the generalized non-orthogonal 2-D 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 (LMS) based algorithms. The aim is to achieve minimum mean squared error for the reconstructed image from the set of the Gabor coefficients. Application of this scheme in image data reduction is demonstrated in the simulation results

Keywords

convergence of numerical methods; data compression; image coding; image recognition; image representation; image segmentation; learning (artificial intelligence); least squares approximations; neural nets; transforms; Gabor coefficients; Gabor transform extraction; RLS learning algorithm; convergence; fast learning algorithm; image data reduction; minimum mean squared error; neural network-based approach; nonorthogonal 2D Gabor transform representation; reconstructed image; recursive least squares; Convergence; Data compression; Discrete transforms; Fourier transforms; Image reconstruction; Image representation; Lattices; Least squares approximation; Neural networks; Time frequency analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on

Conference_Location

London

Print_ISBN

0-7803-1915-X

Type

conf

DOI

10.1109/ISCAS.1994.409163

Filename

409163