摘要
提出一种应用于移动互联网的多源生物特征实时身份认证系统,克服了现有系统仅采用单一生物特征来源导致身份识别准确度低的问题。采取移动终端与网络服务器相结合的架构,在移动终端采集用户人脸与指纹等多个生物特征信息,在网络服务器端进行多源生物特征信息融合识别处理,并采取直接内存读取、裁剪帧图像和划分兴趣区域等方法减少终端运算负荷以实现系统实时性。实验结果表明,本系统在自然场景下的用户身份识别准确度和鲁棒性要高于目前移动互联网身份认证主流系统。
A design scheme of Real-time identity authentication system for multi-source biometric features in mobile internet is proposed,this system overcomes the problem of low accuracy of identity recognition by using single biometric source.The system take a mobile terminal and a network server combination architecture,the mobile terminal collect user face and fingerprint information,fusion identification processing of multi source biometric information at network server,and take direct memory read,cut frame image and division of interest area method to reduce the terminal operational load to achieve Real-time system.The experimental results show that the accuracy and robustness of the system in the natural scene are higher than the current mainstream authentication system in the mobile internet field.
作者
马祥
赵富贵
MA Xiang;ZHAO Fugui(School of Information Engineering, Chang＇ an University, Xi＇ an 710064, China)
出处
《电视技术》
北大核心
2017年第11期162-166,180,共6页
Video Engineering
基金
国家自然科学基金项目(61572083)
中央高校基本科研业务费专项资金项目(310824153508
310824173401)
关键词
移动互联网
移动终端
多源生物特征
身份认证
Mobile internet
Mobile terminal
Multi-source biometric features
Identity authentication
