Communication science et technologie
Volume 4, Numéro 1, Pages 31-38
2006-01-01
Artificial Neural Network & Mul Tilevel 2-d Wavelet Decomposition Code-based Iris Recognition.
Authors : R. Adjoudj . A. Boukelif .
Abstract
An iris recognition in volves analysions factures found ill the colored ring of tissue that surrounds the pupil. This biometric has the potential for higher than average template-thatching performance. Easy of use and system integration has not traditionally been strong points with iris scanning deviees but as nel\'products emerge, in tproventents should be expected. This document demonstrates how a iris recognition system clay he designed by art ific ial neural network kasha a thatching/recognizing algorithm. Which use Multilevel 2-D wavelet decomposition code of' iris image. Note that the training process did not consist of a single cali to a training function. Instead, thenet work lI'as trained severa! Times on various input ideal and noisy images coded by Multilevel 2-DWavelet decomposition, the images which contents iris.fil this case training ({network 0/1 different sets of noisy images forced the network to Learn how to deal with noise, a common problem in the real world.
Keywords
Biometrie, Pattern Recognition, Artificial Neural Network, WaveletDecomposition and Image processing.
Les articles similaires
Benkaddou Mohammed Kamel
.
pages 7-13.
Ouadfeul Sid Ali
.
Zaourar Naima
.
Boudella Amar
.
Hamoudi Mohamed
.
pages 103-118.
Gourine B
.
pages 139-160.
Mekki H.
.
Mellit A.
.
Salhi H.
.
Guessoum A.
.
pages 001-009.
