改进的马氏距离动态时间规整手势认证方法

doi:10.11772/j.issn.1001-9081.2015.05.1467

计算机应用 ›› 2015, Vol. 35 ›› Issue (5): 1467-1470.DOI: 10.11772/j.issn.1001-9081.2015.05.1467

改进的马氏距离动态时间规整手势认证方法

周治平, 苗敏敏

江南大学物联网工程学院, 江苏无锡 214122

收稿日期:2014-12-05 修回日期:2015-01-09 发布日期:2015-05-14 出版日期:2015-05-10
通讯作者: 苗敏敏
作者简介:周治平(1962-),男,江苏无锡人,教授,博士,主要研究方向:图像与信号处理、信息安全; 苗敏敏(1989-),男,浙江舟山人,硕士研究生,主要研究方向:信息系统、信息安全.
基金资助:
2012年度教育部中国移动科研基金资助项目(MCM20122062).

Dynamic time warping gesture authentication algorithm based on improved Mahalanobis distance

ZHOU Zhiping, MIAO Minmin

School of Internet of Things Engineering, Jiangnan University, Wuxi Jiangsu 214122, China

Received:2014-12-05 Revised:2015-01-09 Online:2015-05-14 Published:2015-05-10

摘要/Abstract

摘要：

针对现有动态手势认证方法普遍采用的动态时间规整(DTW)算法在计算欧氏距离(ED)时各维特征向量被同等对待且各维特征间的相关性被忽视等问题,提出一种改进的马氏距离动态时间规整手势认证方法.通过手机内置三轴加速度传感器实时获取动态手势信号,经数据预处理后由改进动态时间规整算法进行加速度信号相似性度量,在计算过程中根据协方差矩阵特点进行时间复杂度优化,最后根据模板匹配法得出认证结论.实验结果表明,经改进后等错率(EER)由3.02%降至1.39%,经优化后认证响应时间平均降低87.84%.该方法进一步提高了动态手势认证精确度,同时实时性良好.

关键词: 加速度传感器, 动态手势认证, 马氏距离, 欧氏距离, 动态时间规整

Abstract:

Concerning the problem that Euclidean Distance (ED) treats each feature equally and cannot take account of the correlations between features in Dynamic Time Warping (DTW) method which is commonly used in dynamic gesture authentication, a DTW gesture authentication algorithm based on improved Mahalanobis Distance (MD) was put forward. It utilized embedded three-axial accelerometer to capture the real-time dynamic hand signals, acceleration signal similarity was measured by the improved DTW method after data preprocessing, and according to the characteristics of the covariance matrix, the time complexity was optimized in the process of calculation, finally the result of authentication was got by template matching method. The experimental results show that the Equal Error Rate (EER) decreases from 3.02% to 1.39% and the average authentication response time reduces by 87.84% after optimization. The proposed method improves the accuracy of the dynamic hand gesture authentication and has a good real-time performance at the same time.

Key words: accelerometer, dynamic gesture authentication, Mahalanobis Distance (MD), Euclidean Distance (ED), Dynamic Time Warping (DTW)

中图分类号:

TP391

周治平, 苗敏敏. 改进的马氏距离动态时间规整手势认证方法[J]. 计算机应用, 2015, 35(5): 1467-1470.

ZHOU Zhiping, MIAO Minmin. Dynamic time warping gesture authentication algorithm based on improved Mahalanobis distance[J]. Journal of Computer Applications, 2015, 35(5): 1467-1470.

参考文献

[1] SARAVANAN V, SINDHUJA R. Iris authentication through gabor filter using DSP processor[C]// Proceedings of the 2013 IEEE Conference on Information and Communication Technologies. Piscataway: IEEE, 2013: 568-571.
[2] BARRA S, De MARSICO M, GALDI C, et al. FAME: face authentication for mobile encounter[C]// Proceedings of the 2013 4th IEEE Workshop on Biometric Measurement and Systems for Security and Medical Applications. Piscataway: IEEE,2013:1-7.
[3] LI X, LIU T, DENG S, et al. Fast recognition of hand vein with SURF descriptors[J]. Chinese Journal of Scientific Instrument, 2011, 32(4):831-836.(李秀艳, 刘铁根, 邓仕超, 等.基于SURF算子的快速手背静脉识别[J]. 仪器仪表学报,2011, 32(4):831-836.)
[4] ZHANG Z, TIAN G. Design and implementation of identity authentication model based on keystroke rhythm[J].Journal of Computer Applications,2009,29(10):2799-2801.(张治元,田国忠.基于击键韵律的身份认证模型设计与实现[J].计算机应用,2009,29(10):2799-2801.)
[5] CHONG M K, MARSDEN G, GELLERSEN H. GesturePIN: using discrete gestures for associating mobile devices[C]// Proceedings of the 12th International Conference on Human Computer Interaction with Mobile Devices and Services. New York: ACM, 2010:261-264.
[6] OKUMURA F, KUBOTA A, HATORI Y, et al. A study on biometric authentication based on arm sweep action with acceleration[C]// Proceedings of the 2006 International Symposium on Intelligent Signal Processing and Communications. Piscataway:IEEE, 2007:219-222.
[7] MATSUO K, OKUMURA F, HASHIMOTA M, et al. Arm swing identification method with template update for long term stability[C]// Proceedings of the 2007 International Conference on Advances in Biometrics. Heidelberg:Springer-Verlag, 2007:211-221.
[8] LIU J Y. User evaluation of lightweight user authentication with a single tri-axis accelerometer[C]// Proceedings of the 11th International Conference on Human-Computer Interaction with Mobile Devices and Services. New York: ACM,2009: 15-18.
[9] CASANOVA J G, SANCHEZ A C, GONZALO B, et al. Time series distance measures to analyze in-air signatures to authenticate users on mobile phones[C]// Proceedings of the 2011 IEEE International Carnahan Conference on Security Technology. Piscataway:IEEE, 2011: 1-7.
[10] CASANOVA J G, SANCHEZ A C, GONZALO B, et al. Acceleration axis selection in biometric technique based on gesture recognition[C]// Proceedings of the 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Piscataway: IEEE,2010:360-363.
[11] CASANOVA J G, SANCHEZ A C, GONZALO B, et al. Score optimization and template updating in a biometric technique for authentication in mobiles based on gestures[J]. Journal of Systems and Software,2011,84(11):2013-2021.
[12] CASANOVA J G, SANCHEZ A C, DESANTOS S A, et al. A real-time in air signature technique using a mobile device embedding an accelerometer[C]// Proceedings of the 2nd International Conference on Networked Digital Technologies. Heidelberg: Springer-Verlag, 2010:497-503.
[13] GONZALO B, SANCHEZ A C, CASANOVA J G, et al. Analysis of pattern recognition techniques for in-air signature biometrics[J].Pattern Recognition, 2011, 44(10):2468-2478.
[14] KEOGH E J, CHU S, HART D,et al. An online algorithm for segmenting time series[C]// Proceedings of the 1st IEEE International Conference on Data Mining. Washington, DC: IEEE Computer Society, 2001:289-296.
[15] QIAO Y, WANG X, XU C. Learning Mahalanobis distance for DTW based online signature verification[C]// Proceedings of the 2011 IEEE International Conference on Information and Automation. Piscataway:IEEE,2011:334-338.

改进的马氏距离动态时间规整手势认证方法

Dynamic time warping gesture authentication algorithm based on improved Mahalanobis distance

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	孙林, 刘梦含. 基于自适应布谷鸟优化特征选择的K-means聚类[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 831-841.
[2]	邱莲鹏, 宋承云. 噪声鲁棒的动态时间规整算法[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1855-1860.
[3]	张海永, 方贤进, 张恩皖, 李宝玉, 彭超, 穆健翔. 基于测量报告信号聚类的指纹定位方法[J]. 《计算机应用》唯一官方网站, 2023, 43(12): 3947-3954.
[4]	赵一鉴, 林利, 王茜蒨, 闻鹏, 杨东. 基于大地距离计算相似度的海上目标轨迹预测[J]. 《计算机应用》唯一官方网站, 2023, 43(11): 3594-3598.
[5]	张瑛琪, 彭大卫, 李森, 孙莹, 牛强. 基于单标签射频识别的唇语识别算法[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1762-1769.
[6]	陈学勤, 陶涛, 张钟旺, 王一蕾. 融合成对编码方案及二维卷积神经网络的长短期会话推荐算法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1347-1354.
[7]	沈忱, 邰凌翔, 彭煜玮. 面向自动参数调优的动态负载匹配方法[J]. 计算机应用, 2021, 41(3): 657-661.
[8]	夏伦腾, 张莉. 基于K近邻和动态时间规整算法的盲人物联网手杖系统[J]. 计算机应用, 2020, 40(8): 2441-2448.
[9]	黄功, 赵永平, 谢云龙. 基于局部密度的加权一类支持向量机算法及其在涡轴发动机故障检测中的应用[J]. 计算机应用, 2020, 40(3): 917-924.
[10]	孔菁, 郭渊博, 刘春辉, 王一丰. 基于智能手机运动传感器的步态特征身份识别方法[J]. 计算机应用, 2019, 39(6): 1747-1752.
[11]	刘帅, 刘长良, 甄成刚. 风电机组齿轮箱的多变量时间序列故障预警[J]. 计算机应用, 2019, 39(4): 1229-1233.
[12]	李强, 于凤芹. 改进音高轮廓创建和选择的旋律提取算法[J]. 计算机应用, 2018, 38(8): 2411-2415.
[13]	陈虹, 肖越, 肖成龙, 宋好. 基于SIFT算子融合最大相异系数的自适应图像匹配算法[J]. 计算机应用, 2018, 38(5): 1410-1414.
[14]	谢小雨, 刘喆颉. 基于肌电信号和加速度信号的动态手势识别方法[J]. 计算机应用, 2017, 37(9): 2700-2704.
[15]	张明洋, 陈剑, 闻英友, 赵宏, 王玉刚. 基于动态时间规整距离指纹匹配的Wi-Fi网络室内定位算法[J]. 计算机应用, 2017, 37(6): 1550-1554.