基于D-LDA与最近特征分类法的眼虹膜识别系统  

Human iris recognition system based on D-LDA and nearest feature classifiers

作　　者：陈添丁[1] 郎燕峰[1] 

机构地区：[1]浙江工商大学通信与信息技术研究所,浙江杭州310035

出　　处：《计算机工程与设计》2006年第23期4516-4520,共5页Computer Engineering and Design

摘　　要：以3个主要处理阶段来实现一个高识别率的虹膜识别系统。撷取人眼图像进而分离出虹膜图像,再利用图像处理予以改善,使得虹膜图像更适于后续的识别。接着建立虹膜的特征向量,在虹膜图像展开的过程中,解决了虹膜图像旋转不变性的问题,然后利用直接线性判别分析(D-LDA)的方式进行特征抽取,使得所产生出来的特征向量拥有最大类别间距离与最小类别内距离的特性。最后,探讨多种最近特征分类法与其识别效果,并将上述方法设计完成一套眼虹膜识别系统。实验结果显示,在样本特征向量数较少的情况下识别率有96.47%,如果在每个类别中增加样本特征向量的数量,则系统的识别率可以达到98.50%。A human iris recognition system with a high recognition rate is presented. The iris recognition system consists ofthree major processing phases. First, images of human＇s eyes from a web camera is captured, and iris images from them is obtained. We further manipulate the iris images using digital image processing techniques, so that the resulting iris images are suited to recognition. Second, the feature vectors from the iris images is made. Before extraction of feature vectors, we must unwrap the iris images. In this phase, the problem of rotation invariant is solved. We then adopt direct linear discriminant analysis to extract feature vectors such that the distance between the feature vectors of different classes is the largest but the distance between those in the same class is the smallest. Finally, the nearest feature classifiers to discriminate the feature vectors is employed. To verify the effectiveness of the proposed methods, we realize a human iris recognition system. The experimental results show that the recognition rate achieves 96.47 % in the case of fewer sampling feature vectors, whereas it can attain 98.50 % if more sampling feature vectors are added to each class.

关 键 词：虹膜识别系统 最近特征分类法 直接线性判别分析 旋转不变性 样本特征向量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]