首页> 外文会议>Conference on Dynamics of Systems, Mechanisms and Machines >Perspective Neural Network Algorithms for Dynamic Biometric Pattern Recognition in the Space of Interdependent Features
【24h】

Perspective Neural Network Algorithms for Dynamic Biometric Pattern Recognition in the Space of Interdependent Features

机译:相互依赖特征空间中动态生物特征识别的透视神经网络算法

获取原文

摘要

A model of neurons for biometric authentication, capable of efficient processing of highly dependent features, based on the agreement criteria (Gini, Cramer-von-Mises, Kolmogorov-Smirnov, the maximum of intersection areas of probability densities) is proposed. An experiment was performed on comparing the efficiency of neurons based on the proposed model and neurons on the basis of difference and hyperbolic Bayesian functionals capable of processing highly dependent biometric data. Variants of construction of hybrid neural networks, that can be trained on a small number of examples of a biometric pattern (about 20), are suggested. An experiment was conducted to collect dynamic biometric patterns, in the experiment 90 people entered handwritten and voice patterns during a month. Intermediate results on recognition of subjects based on hybrid neural networks were obtained. Number of errors in verification of a signature (handwritten password) was less than 2%, verification of a speaker by a fixed passphrase was less than 6%. The testing was carried out on biometric samples, obtained after some time period after the formation of training sample.
机译:提出了一种用于生物特征认证的神经元模型,该模型能够基于协议标准(Gini,Cramer-von-Mises,Kolmogorov-Smirnov,概率密度的最大交集区域)有效处理高度依赖的特征。进行了一项实验,比较了基于所提出的模型的神经元的效率和基于差异和能够处理高度依赖的生物特征数据的双曲线贝叶斯函数的神经元的效率。建议了可以在少量生物特征模式示例(约20个)上训练的混合神经网络构造的变体。进行了一项收集动态生物特征识别模式的实验,该实验在一个月内输入了90个人的手写和语音模式。获得了基于混合神经网络的对象识别的中间结果。签名(手写密码)验证错误的数量少于2%,使用固定密码验证说话者的比例少于6%。测试是在形成训练样本后一段时间内获得的生物特征样本上进行的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号