Abstract
Abstract Iris recognition is regarded as the most reliable and accurate biometric identification system available. A biometric system provides automatic identification of an individual based on a unique feature or stable characteristic possessed by the individual. This research involves intelligent iris recognition system. For determination of the recognition performance of the iris, CASIA database of digital grayscale eye image was used. This database was then used to process the illumination which is the most important problem in iris recognition. (42) images for different irises used for training, obtained from CASIA, by extension (bmp), and (30) other snapshots for the same irises for testing because CASIA database provided more than one snapshot for each iris, the feature extraction implemented depended on extract the statistical values of (variance, standard deviation, skweness, kurtosis) and seven invariant moments for each image, the results of simulations of Elman artificial neural network that possessed dynamic memory which used as a tool to take decision, illustrate the effectiveness recognition in training 100% and in testing recognition accuracy = (93.33%). The software to perform iris recognition uses Matlab® (2010) development environment.
