Study on Application of HMM to Online Signature Verification Based on Differences of Matched Segment
ZOU Jie1, WU Zhong-Cheng1,2
1.Automation Control Group,High Magnetic Field Laboratory,Hefei Institutes of Physical Science,Chinese Academy of Sciences,Hefei 230031 2.Institute of Intelligent Machines,Chinese Academy of Sciences,Hefei 230031
Abstract An approach of hidden markov model (HMM) to online signature verification is proposed, which uses difference values obtained by segmentation dynamic time wrapping (DTW) as observations of model. Firstly, the correspondences of the critical points in signatures are made by bidirectional backward-merging dynamic time wrapping algorithm. Then, the subtle differences are calculated by classical dynamic time wrapping algorithm. These differences are utilized to train the HMM. The meanings of models states are defined as degrees of similarity, and the HMM topology is ergodic. The validity of the proposed approach is verified on SVC2004 signatures database.
ZOU Jie,WU Zhong-Cheng. Study on Application of HMM to Online Signature Verification Based on Differences of Matched Segment[J]. , 2011, 24(4): 555-560.
[1] Plamondon R,Lorette G.Automatic Signature Verification and Writer Identification-The State of the Art. Pattern Recognition,1989,22 (2): 107-131 [2] Jain A K,Griess F D,Connell S D.On-Line Signature Verification.Pattern Recognition,2002,35(12): 2963-2972 [3] Sakoe H,Chiba S.Dynamic Programming Algorithm Optimization for Spoken Word Recognition.IEEE Trans on Acoustics,Speech and Signal Processing,1978,26(1): 43-49 [4] Feng Hao,Wah C C.Online Signature Verification Using a New Extreme Points Warping Technique.Pattern Recognition Letters,2003,24(16): 2943-2951 [5] Fierrez J,Ortega-Garcia J,Ramos D,et al.HMM-Based On-Line Signature Verification: Feature Extraction and Signature Modeling.Pattern Recognition Letters,2007,28(16): 2325-2334 [6] Pascual-Gaspar J M,Cardenoso-Payo V.On-Line Signature Verification Using Hidden Markov Models with Number of States Estimation from the Signature Duration // Proc of the Biometrics Symposium.Baltimore,USA: 2007: 1-6 [7] Muramatsu D,Matsumoto T.An HMM On-Line Verifier Incorporating Signature Trajectories // Proc of the 7th International Conference on Document Analysis and Recognition.Edinburgh,Scotland,2003,Ⅰ: 438-442 [8] Wan Liang,Wan Bin.Online Signature Verification with Two-Stage Statistical Models // Proc of the 8th International Conference on Document Analysis and Recognition.Seoul,Koren,2005: 282-286 [9] Yuan Yuliang,Shen Feng,Yang Fei,et al.The Design and Implementation of a Dynamic Handwritten Signature Verification System Based on HMM.Pattern Recognition and Artificial Intelligence,2004,17(2): 146-150 (in Chinese) (袁余良,沈 峰,杨 飞,等.一种基于HMM的动态手写签名认证系统的设计与实现.模式识别与人工智能,2004,17(2): 146-150) [10] Shafiei M M,Rabiee H R.A New On-Line Signature Verification Algorithm Using Variable Length Segmentation and Hidden Markov Models // Proc of the 7th International Conference on Document Analysis and Recognition.Edinburgh,Scotland,2003,Ⅰ: 443-446 [11] Zou Mingfu,Tong Jianjun,Liu Changping,et al.Online Signature Verification Using Local Shape Analysis // Proc of the 7th International Conference on Document Analysis and Recognition.Edinburgh,Scotland,2003,Ⅰ: 3-6 [12] Van Bao L,Garcia-Salicetti S,Dorizzi B.On Using the Veterbi Path along with HMM likelihood Information for Online Signature Verification.IEEE Trans on Systems,Man and Cybernetics.2007,37(5): 1237-1247 [13] Quan Zhonghua,Huang Deshuang,Liu Kunhong,et al.A Hybrid HMM/ANN Based Approach for Online Signature Verification // Proc of the International Joint Conference on Neural Networks.Orlando,USA,2007: 402-405 [14] Yeung D Y,Chang Hong,Xiong Yimin,et al.SVC2004: First International Signature Verification Competition // Proc of the International Conference on Biometric Authentication.Hong Kong,China,2004: 16-22 [15] Lawrence R.Rabiner.A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition // Proc of the IEEE,1989,77(2): 257-286 [16] Hu Jianying,Brown M K,Turin W.HMM Based On-Line Handwriting Recognition.IEEE Trans on Pattern Analysis and Machine Intelligence,1996,18(10): 1039-1045 [17] Yang Jie,Xu Yangsheng,Chen C S.Human Action Learning via Hidden Markov Model.IEEE Tranc on Sytems,Man and Cybernetics,1997,27(1): 34-44 [18]Li Bin,Zhang D,Wang Kuanquan.Improved Critical Point Correspondence for On-Line Signature Verification.International Journal of Information Technology,2006,12(7): 45-56 [19] Zou Jie,Wu Zhongcheng.Online Signature Verification System Based on Support Vector Data Description.Pattern Recognition and Artificial Intelligence,2011,24(2): 284-290 (in Chinese) (邹杰,吴仲城.基于支持向量数据描述的在线签名认证系统.模式识别与人工智能,2011,24(2): 284-290)
2011, Vol. 24 
