As a part of a growing information society, nowadays the issue of security is more crucial than ever. In order to achieve high level of security, the potential of accurately recognize subjects based on their unique measurable physiological or behavioral characteristics has been receiving an increased concern by the research and development community. As biometrics has advanced, iris has been considered a preferred trait because unique pattern texture, lifetime stability, and regular shape contribute to good segmentation and recognition performance. The incredible uniqueness of iris patterns as well as the ability to capture iris images non-invasively has motivated us to develop automated system for iris recognition based on 2-D iris images. The 2DPCA (two-dimensional Principal Component Analysis) and GA (Genetic Algorithm) have been used as feature extraction and feature selection techniques for reducing the dimensionality of iris features without the loss of relevant Information. The Back Propagation Neural Network (BPNN) is implemented using Levenberg–Marquardt’s learning rule for iris recognition. The experimental results illustrated that the 2DPCA-GA achieved a high classification accuracy of 96.40 %.

作为不断发展的信息社会的一部分，如今安全问题比以往任何时候都更加重要。为了实现高级别的安全性，基于研究人员独特的可测量的生理或行为特征来准确识别受试者的潜力已受到研究与开发界的越来越多的关注。随着生物识别技术的发展，虹膜被认为是首选特征，因为独特的图案纹理，寿命稳定性和规则形状有助于良好的分割和识别性能。虹膜图案的独特性以及无创捕获虹膜图像的能力促使我们开发基于二维虹膜图像的虹膜识别自动化系统。2DPCA（二维主成分分析）和GA（遗传算法）已被用作特征提取和特征选择技术，用于在不损失相关信息的情况下降低虹膜特征的维数。反向传播神经网络（BPNN）使用Levenberg–Marquardt的虹膜识别学习规则来实现。实验结果表明，2DPCA-GA的分类精度达到96.40％。