基于步态识别的移动设备身份认证模型
|
摘要
智能移动设备遗失时,隐私泄露是一个大问题。现在的生物特征识别技术必须借助相应的辅助设备,如指纹识别、人脸识别等,认证操作复杂且成本较高。针对以上问题,该文提出一种基于步态识别的移动设备身份认证模型。在训练阶段,通过移动设备自带的加速度传感器对用户在日常生活中不同行为下的步态数据进行收集,提取特征形成特征向量并建立步态模型;在识别阶段,利用基于神经网络的模型匹配算法进行身份识别。系统实现采用C/S架构,所有传输数据采用国密SMS4对称加密算法进行加密,保证了数据传输的安全性。实验表明,神经网络算法的平均识别率为78.13%,综合反馈机制之后,可以达到98.96%的认证准确率。
Privacy disclosure is a big problem when smart mobile devices lost. Now, the biometric technologies must rely on the corresponding auxiliary equipment, such as fingerprint recognition, face recognition,resulting in the authentication is complex and costly. To solve these problems, a gait biometrics-based mobile device authentication solution is proposed in this paper. In the training phase, the gait data of different behaviors of users in daily life are collected by the accelerometer in the mobile device. Then, the feature is extracted to construct feature vector and establish the gait model of users. The model matching algorithm based on the neural network is used to achieve the purpose of identification during the identification phase. The C/S architecture is applied to the implementation of the system. In order to ensure the security of network data transmission, all the transmission data is encrypted by SMS4 symmetric encryption algorithm. Lots of experiments show that the average recognition rate of neural network algorithm is 78.13 percent, and integrating the feedback mechanism, the authentication accuracy can up to 98.96 percent.
Privacy disclosure is a big problem when smart mobile devices lost. Now, the biometric technologies must rely on the corresponding auxiliary equipment, such as fingerprint recognition, face recognition,resulting in the authentication is complex and costly. To solve these problems, a gait biometrics-based mobile device authentication solution is proposed in this paper. In the training phase, the gait data of different behaviors of users in daily life are collected by the accelerometer in the mobile device. Then, the feature is extracted to construct feature vector and establish the gait model of users. The model matching algorithm based on the neural network is used to achieve the purpose of identification during the identification phase. The C/S architecture is applied to the implementation of the system. In order to ensure the security of network data transmission, all the transmission data is encrypted by SMS4 symmetric encryption algorithm. Lots of experiments show that the average recognition rate of neural network algorithm is 78.13 percent, and integrating the feedback mechanism, the authentication accuracy can up to 98.96 percent.
引文
[1]FAURE F,DEBUNNE G,CANI-GASCUEL M P,et al.Dynamic analysis of human walking[C]//Proceedings of the Eurographics Workshop.Budapest:[s.n.],1997:53-65.
[2]MANTYJARVI J,LINDHOLM M,VILDJIOUNAITE E,et al.Identifying users of portable devices from gait pattern with accelerometers[J].IEEE International Conference on Acoustics,2005,2(2):973-976.
[3]殷海艳,刘波.基于部位检测的人体姿态识别[J].计算机工程与设计,2013,34(10):3540-3544.YIN Hai-yan,LIU Bo.Recognition of human pose based on position detection[J].Computer Engineering and Design,2013,34(10):3540-3544.
[4]袁立,穆志纯,徐正光,等.基于人耳生物特征的身份识别[J].模式识别与人工智能,2005,18(3):56-61.YUAN Li,MU Zhi-chun,XU Zheng-guang,et al.Identity recognition based on human ear biometrics[J].Pattern Recognition and Artificial Intelligence,2005,18(3):56-61.
[5]ROHAN B,ANIRUDDHA S,KINGSHUK C.Gait based people identification system using multiple switching kinects[C]//International Conference on Intelligent Systems Design&Applications.[S.l.]:IEEE,2013:182-187.
[6]姜鸣,王哲龙,刘晓博,等.基于BSN和CHMMs的人体日常动作识别方法研究[J].大连理工大学学报,2013,53(1):121-126.JIANG Ming,WANG Zhe-long,LIU Xiao-bo,et a1.Research on human daily activity recognition method based on BSN and CHMMs[J].Journal of Dalian University of Technology,2013,53(1):121-126.
[7]UGULINO W,CARDADOR D,VEGA K,et a1.Wearable computing:Accelerometers’data classification of body postures and movements[M].[S.l.]:Springer,2012,7(2):52-61.
[8]张君宽.基于BP神经网络步态识别的研究[J].中国安防,2016(Z1):99-101.ZHANG Jun-kuan.Research on BP neural network gait recognition[J].China Security,2016(Z1):99-101.
[9]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Quantum information splitting of arbitrary two-qubit state by using four-qubit cluster state and Bell-state[J].Quantum Information Processing,2015,14(3):1103-1116.
[10]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Quantum information splitting of arbitrary three-qubit state by using seven-qubit entangled state[J].International Journal of Theoretical Physics,2015,54(6):2068-2075.
[11]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li.Quantum information splitting of a two-qubit Bell state using a four-qubit entangled state[J].Chinese Physical C,2015,39(4):26-30.
[12]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li.Quantum information splitting of arbitrary three-qubit state by using four-qubit cluster state and GHZ-state[J].International Journal of Theoretical Physics,2015,54(4):1142-1153.
[13]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Quantum information splitting of arbitrary three-qubit state by using seven-qubit entangled state[J].International Journal of Theoretical Physics,2015,54(6):2068-2075.
[14]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Splitting unknown qubit state using five-qubit entangled state[J].International Journal of Theoretical Physics,2016,55(4):1962-1972.
[2]MANTYJARVI J,LINDHOLM M,VILDJIOUNAITE E,et al.Identifying users of portable devices from gait pattern with accelerometers[J].IEEE International Conference on Acoustics,2005,2(2):973-976.
[3]殷海艳,刘波.基于部位检测的人体姿态识别[J].计算机工程与设计,2013,34(10):3540-3544.YIN Hai-yan,LIU Bo.Recognition of human pose based on position detection[J].Computer Engineering and Design,2013,34(10):3540-3544.
[4]袁立,穆志纯,徐正光,等.基于人耳生物特征的身份识别[J].模式识别与人工智能,2005,18(3):56-61.YUAN Li,MU Zhi-chun,XU Zheng-guang,et al.Identity recognition based on human ear biometrics[J].Pattern Recognition and Artificial Intelligence,2005,18(3):56-61.
[5]ROHAN B,ANIRUDDHA S,KINGSHUK C.Gait based people identification system using multiple switching kinects[C]//International Conference on Intelligent Systems Design&Applications.[S.l.]:IEEE,2013:182-187.
[6]姜鸣,王哲龙,刘晓博,等.基于BSN和CHMMs的人体日常动作识别方法研究[J].大连理工大学学报,2013,53(1):121-126.JIANG Ming,WANG Zhe-long,LIU Xiao-bo,et a1.Research on human daily activity recognition method based on BSN and CHMMs[J].Journal of Dalian University of Technology,2013,53(1):121-126.
[7]UGULINO W,CARDADOR D,VEGA K,et a1.Wearable computing:Accelerometers’data classification of body postures and movements[M].[S.l.]:Springer,2012,7(2):52-61.
[8]张君宽.基于BP神经网络步态识别的研究[J].中国安防,2016(Z1):99-101.ZHANG Jun-kuan.Research on BP neural network gait recognition[J].China Security,2016(Z1):99-101.
[9]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Quantum information splitting of arbitrary two-qubit state by using four-qubit cluster state and Bell-state[J].Quantum Information Processing,2015,14(3):1103-1116.
[10]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Quantum information splitting of arbitrary three-qubit state by using seven-qubit entangled state[J].International Journal of Theoretical Physics,2015,54(6):2068-2075.
[11]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li.Quantum information splitting of a two-qubit Bell state using a four-qubit entangled state[J].Chinese Physical C,2015,39(4):26-30.
[12]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li.Quantum information splitting of arbitrary three-qubit state by using four-qubit cluster state and GHZ-state[J].International Journal of Theoretical Physics,2015,54(4):1142-1153.
[13]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Quantum information splitting of arbitrary three-qubit state by using seven-qubit entangled state[J].International Journal of Theoretical Physics,2015,54(6):2068-2075.
[14]LI Dong-fen,WANG Rui-jin,ZHANG Feng-li,et al.Splitting unknown qubit state using five-qubit entangled state[J].International Journal of Theoretical Physics,2016,55(4):1962-1972.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |