An efficient iris coding based on gauss-laguerre wavelets

  • Authors:

  • H. Ahmadi;A. Pousaberi;A. Azizzadeh;M. Kamarei

  • Affiliations:

  • Dept. of Electrical and Computer Engineering, University of Tehran and University of British Columbia;Dept. of Electrical and Computer Engineering, University of Tehran;Research Center, Ministry of Communication, Tehran, Iran;Dept. of Electrical and Computer Engineering, University of Tehran

  • Venue:
  • ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper preliminary results of a new iris recognition algorithm using Gauss-Laguerre filter of circular harmonic wavelets are presented. Circular harmonic wavelets (CHWs) applied in this paper for iris pattern extraction, are polar-separable wavelets with harmonic angular shape. The main focus of this paper is on iris coding using Gauss-Laguerre CHWs which constitute a family of orthogonal functions satisfying wavelet admissibility condition required for multiresolution pyramid structure. It is shown that Gauss-Laguerre wavelets having rich frequency extraction capabilities are powerful tools for coding of iris patterns. By judicious tuning of Laguerre parameters, a 256-byte binary code is generated for each iris. A fast matching scheme based on Hamming distance is used to compute the similarity between pairs of iris codes. Preliminary experimental results on CASIA and our database indicate that the performance of the proposed method is highly accurate with zero false rate and is comparable with Daugman iris recognition algorithm well publisized in literature.