Elsevier

Signal Processing

Volume 31, Issue 2, March 1993, Pages 229-233
Signal Processing

Short communication
A fast implementation of the discrete 2-D Gabor transform

https://doi.org/10.1016/0165-1684(93)90068-LGet rights and content

Abstract

An FFT-based gradient descent method for computing the non-orthogonal Gabor transform of a two-dimensional discrete signal I[x,y] is described. When operating on images consisting of P × Q pixels divided into sub-images with M × N pixels, the estimated gain in computational speed over a neural network method proposed by Daugman is by a factor of kMN, where k = 10/[3 log2(4MN) +4].

Zusammenfassung

Eine Gradientenmethode auf FFT-Basis zur Berechnung der nicht-orthogonalen Gabortranformation eines zweidimensionalen diskreten Signals I(x,y) wird beschrieben. Sie wird angewandt auf Bilder die aus P × Q Pixeln bestehen und in Teilbilder mit M × N Pixeln zerlegt werden; in diesem Fall entspricht der geschätzte Gewinn bei der Rechengeschwindigkeit gegenüber einem Verfahren das auf einem neuronalen Netzwerk beruht und von Daugman vorgeschlagen wurde, einem Faktor kMN, wobei k = 10/[3 log2(4MN) +4].

Résumé

Nous décrivons une méthode de descente selon le gradient basée sur la FFT pour le calcul de la transformée de Gabor non orthogonale d'un signal discret bi-dimensionnel I[x,y]. Lorsque l'opération s'effectue sur des images consistant en P × Q pixels divisées en sous images de M × N pixels, le gain estimé en vitesse de calcul par rapport à une méthode basée sur un réseau de neurones proposée par Daugman est kMN, où k = 10/[3 log2(4MN) +4].

References (10)

  • L Auslander et al.

    The discrete Zak transform application to time-frequency analysis and synthesis of non-stationary Signals

    IEEE Trans. Signal Process

    (1991)
  • M Bastiaans

    Gabor's expansion of a signal into elementary signals

  • J Daugman

    Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters

    J. Opt. Soc. Amer.

    (1985)
  • J Daugman

    Complete discrete 2-D Gabor transform by neural networks for image analysis and compression

    IEEE Trans. Acoust. Speech Signal Process.

    (1988)
  • D Gabor

    Theory of communication

    J. Inst. Elec. Eng.

    (1946)
There are more references available in the full text version of this article.

Cited by (3)

  • A Performance Analysis of Fast Gabor Transform Methods

    1997, Graphical Models and Image Processing
  • GIS Optical Partial Discharge Pattarn Identification Based on Two-dimensional Gabor Transform and Image Features

    2021, International Conference on Advanced Electrical Equipment and Reliable Operation, AEERO 2021
  • A novel approach for noise reduction in the gabor time-frequency domain

    2009, VISAPP 2009 - Proceedings of the 4th International Conference on Computer Vision Theory and Applications
View full text