【摘要】 虹膜识别以其唯一性、稳定性和非侵犯性等优点成为生物特征识别中极具发展潜力的身份识别技术。文章提出了一种基于局部小波变换和奇异值分解的虹膜识别算法。该算法首先对虹膜图像实行分窗小波分解,并对各窗口的子带图像作筛选处理,然后通过奇异值分解对筛选后的各子带图像作进一步的特征提取和压缩,得到虹膜识别特征。最后利用加权欧氏距离分类器进行识别。基于CASIA虹膜数据库的实验结果表明了该算法的有效性,为虹膜识别提供了一种新途径。更多还原

【Abstract】 Iris recognition has become a best potential technology of identity authentication in biometric feature recognition because of the advantages of invariability,stability and un-intrusion.Combined with local Wavelet Transform(WT) and Singular Value Decomposition(SVD),an approach for iris recognition is presented in this paper.Firstly,iris image is divided into several sub-images,and wavelet transform is done to them.At the same time,some of the daughter wavelets are selected,which contain most information of iris image.Secondly,the farther feature extraction and compression are applied to these daughter wavelets by way of SVD,and iris recognition features are obtained.Finally,weighted Euclidean distance classifier is utilized in recognition.Experimental results on CASIA(Chinese Academy of Sciences,Institute of Automation) iris database show the method is valid in iris recognition,and a new approach is supplied for iris recognition.更多还原