摘要
空中签名序列长,为了解决传统的全局匹配方法造成的匹配慢、签名的局部信息丢失的问题,提出了对签名数据进行极值点分段再进行距离度量的方法。并针对传统DTW算法在极值点匹配中产生的不同极性极值点错匹配问题,提出了一种基于极值点匹配的改进DTW算法,约束DTW算法的匹配路径规则,避免错误匹配情况。在本地数据库上,系统的误拒率(FRR)和误纳率(FAR)分别达到了4. 15%和3. 82%。实验结果表明,与传统的全局匹配算法相比,先分段再进行相似度度量的方法使系统的认证精度和效率得到了提高。
The sequence of the in-air signature is long,in order to make the signature match faster and take advantage of more local information,this paper proposed a method that used the extreme points to segment the signature data and then measured the distance. Aiming at the mismatch problem of different polarity extreme point in traditional DTW algorithm,this paper proposed an improved DTW algorithm based on extreme point matching,which constrained the matching path of DTW algorithm and avoided error matching between extreme points. It achieved the result FRR: 4. 15% and FAR: 3. 82% on the local database. Experimental results show that,compared with the traditional global distance measurement method,the method that segment first and then measure the distance improves the accuracy and efficiency of the system.
引文
[1] De Luis-GarcíA R,Alberola-López C,Aghzout O,et al. Biometric identification systems[J]. Signal Processing,2003,83(12):2539-2557.
[2] Guerracasanova J,Riossanchez B,Vianamatesanz M,et al. Comfort and security perception of biometrics in mobile phones with widespread sensors[C]//Proc of IEEE Reliable Distributed Systems Workshops. Piscataway,NJ:IEEE Press,2016:13-18.
[3] Abate A F,Nappi M,Riccio D,et al. 2D and 3D face recognition:a survey[J]. Pattern Recognition Letters,2007,28(14):1885-1906.
[4] Kim D,Jung Y,Toh K A,et al. An empirical study on iris recognition in a mobile phone[J]. Expert Systems with Applications,2016,54(7):328-339.
[5] Nanni L,Lumini A. Fusion of color spaces for ear authentication[J].Pattern Recognition,2009,42(9):1906-1913.
[6] Ríos-Sánchez B,Viana-Matesanz M,Sánchez-ávila C,et al. A configurable multibiometric system for authentication at different security levels using mobile devices[C]//Proc of IEEE Reliable Distributed Systems Workshops. Piscataway,NJ:IEEE Press,2016:19-24.
[7] Baldi P,Chauvin Y. Neural networks for fingerprint recognition[J].Neural Computation,2014,5(3):402-418.
[8]张浩,刘志镜.加权DTW距离的自动步态识别[J].中国图象图形学报,2010,15(5):830-836.(Zhang Hao,Liu Zhijing. Automated gait recognition using weighted DTW distance[J]. Journal of Image&Graphics,2010,15(5):830-836.)
[9] Paudel N,Querini M,Italiano G F. Handwritten signature verification for mobile phones[C]//Proc of International Conference on Information Systems Security and Privacy. Berlin:Springer,2016:46-52.
[10]Bala A,Kumar A,Birla N. Voice command recognition system based on MFCC and DTW[J]. International Journal of Engineering Science&Technology,2010,2(12):7335-7342.
[11]Arjona R,Romero-Moreno R,Baturone I. Hardware implementation of a biometric recognition algorithm based on in-air signature[C]//Proc of IEEE Design and Architectures for Signal and Image Processing. Piscataway,NJ:IEEE Press,2015:1-6.
[12]苗敏敏.基于手机内置加速度传感器的动态手势认证方法[D].无锡:江南大学,2015.(Miao Minmin. Dynamic gesture authentication method based on embedded accelerometer in mobile phone[D].Wuxi:Jiangnan University,2015.)
[13] Guerra-Casanova J,Sierra A D S,Pozo G B D. Score optimization and template updating in a biometric technique for authentication in mobiles based on gestures[J]. Journal of Systems&Software,2011,84(11):2013-202.
[14]王尧,孙子文,周治平.一种基于手机加速度传感器的三维手势身份认证方法[J].传感器与微系统,2014,33(8):37-40.(Wang Yao,Sun Ziwen,Zhou Zhiping. A method of 3D gesture identity authentication based on mobile-phone acceleration sensor[J]. Transducer&Microsystem Technologies,2014,33(8):37-40.)
[15] Fang Yuxun,Kang Wenxiong,Wu Qiuxia,et al. A novel videobased system for in-air signature verification[J]. Computers&Electrical Engineering,2017,57(1):1-14.
[16]罗琼.智能手机在线手写签名认证系统设计[D].武汉:武汉理工大学,2014.(Luo Qiong. Design of online handwriting signature verification used in smartphone[D]. Wuhan:Wuhan University of Technology,2014.)
[17]Hao Feng,Chan C W. Online signature verification using a new extreme points warping technique[J]. Pattern Recognition Letters,2003,24(16):2943-2951.
[18]肖辉,胡运发.基于分段时间弯曲距离的时间序列挖掘[J].计算机研究与发展,2005,42(1):72-78.(Xiao Hui,Hu Yunfa. Data mining based on segmented time warping distance in time series database[J]. Journal of Computer Research&Development,2005,42(1):72-78.