排序方式: 共有101条查询结果,搜索用时 15 毫秒
1.
2.
网络接入控制安全越来越得到重视和研究,文中提出一种新颖的生物识别技术,即基于虹膜识别的生物识别方法,它抛弃了使用密码和个人识别码等不可靠的鉴别方法,由于它接近于零的错误接收率和较低的错误拒绝率而具有高安全性. 相似文献
3.
目前的虹膜识别都是采用在图像上提取特征点,并将特征点编码为固定长度的特征数据用于匹配的方式。这种方式使虹膜识别系统易受攻击。为了进一步提高虹膜识别系统的安全性和识别速度,提出了一种基于灰度曲面匹配的虹膜识别方法。该方法抛弃了特征提取和编码等传统操作,在特征分析的基础上直接利用了灰度曲面匹配的思想,首先对两幅图像中的像素灰度做差,得到灰度差曲面,然后求出该灰度差曲面的方差。将此方差作为衡量两个虹膜特征曲面之间距离的依据,并据此判定两个虹膜是否来自同一只眼睛。在给定阈值为40的前提下,正确识别率为96.89%,识别时间为53.2 ms。实验结果证明,该方法识别准确率高,识别速度快。 相似文献
4.
一种基于人眼图像灰度分布特征的虹膜定位算法 总被引:13,自引:3,他引:10
提出了一种基于人眼图像灰度分布特征的虹膜定位算法。该算法不必检测到所有的虹膜边界点,只需要分别在虹膜的内外边界上各检测到3个点即可。然后利用落在同一个边界上的3个点,根据“非共线的3点确定1个圆”的几何原理,计算出边界圆的参数,从而确定虹膜内外边界。对CASIA虹膜图像数据库进行了大量的实验,结果表明,该算法与经典的虹膜定位算法(如Daugman的算法和边缘检测算子结合Hough变换的算法)相比,定位结果更加准确,定位速度大幅度提高。 相似文献
5.
6.
随着近年来图像传感器的快速商用化以及生物识别算法的发展,虹膜识别功能得以应用于移动终端设备。获取虹膜图像是虹膜识别的关键一步,运用ZEMAX光学设计软件设计了一款适用于手机的虹膜识别镜头。该镜头采用豪威科技公司OmniVision_OV2281传感器,采用三片式非球面光学塑料设计,F数为2.3,全视场角为34°,在1/2奈奎斯特频率220 lp/mm处MTF值均大于0.39,且系统总长仅3 mm。根据ZEMAX像质评价方法以及公差分析结果可知,该镜头各项光学指标优良,具有像质好、体积小,质量轻、价格低、容易加工等特点。 相似文献
7.
8.
Alexander B. Manenkov Ioannis G. Tigelis Angelos J. Amditis 《Optics Communications》2007,274(2):333-340
The diffraction phenomenon caused by metal transverse irises placed into an asymmetrical slab waveguide is examined by using the integral equation method. We concentrate on the possibility of controlling the radiation characteristics of the structure by changing the irises positions and the slab waveguide asymmetry. The aperture electric-field distribution is expressed in terms of a finite series of Chebyshev polynomials. The dominant TE guided-mode reflection and transmission coefficients, the near-field distribution and the far-field radiation pattern are calculated, while numerical results are presented for several cases of asymmetrical slab waveguides and different irises’ positions. 相似文献
10.
We consider the problem of discriminating between two independent multivariate normal populations, Np(μ1, Σ1) and Np(μ2, Σ2), having distinct mean vectors μ1 and μ2 and distinct covariance matrices Σ1 and Σ2. The parameters μ1, μ2, Σ1, and Σ2 are unknown and are estimated by means of independent random training samples from each population. We derive a stochastic representation for the exact distribution of the “plug-in” quadratic discriminant function for classifying a new observation between the two populations. The stochastic representation involves only the classical standard normal, chi-square, and F distributions and is easily implemented for simulation purposes. Using Monte Carlo simulation of the stochastic representation we provide applications to the estimation of misclassification probabilities for the well-known iris data studied by Fisher (Ann. Eugen.7 (1936), 179–188); a data set on corporate financial ratios provided by Johnson and Wichern (Applied Multivariate Statistical Analysis, 4th ed., Prentice–Hall, Englewood Cliffs, NJ, 1998); and a data set analyzed by Reaven and Miller (Diabetologia16 (1979), 17–24) in a classification of diabetic status. 相似文献