Human iris recognition using elman neural networks

الملخص EN

The human iris is one of the best biometric features in the human body for pattern recognition.

In this paper, the iris recognition system is described that consist of two main parts : image processing and its recognition.

Image processing follows the capture of image, then followed by image segmentation, then localization of iris region by determining the inner and outer boundaries of the iris region and by removing the eyelashes and eyelids.

To overcome the discrepancies in the iris region, a rectangular shape with constant dimensions is proposed, which is represented by a set of data following the normalization procedure.

Using these data set as input data of the Elman Artificial Neural Networks in order to classify the iris patterns.

The adaptive learning strategy could be applied to verify each iris image of a particular person.

This is done by using MATLAB®2008a.