基于笔段特征和HMM的在线签名认证方法研究<sup>*</sup>

摘要
图/表
参考文献
相关文章 (14)

全文: PDF (722 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要手写签名过程中的书写力包含丰富个人特征.受输入设备所限，目前的在线手写签名认证系统都没有能够充分利用这一信息.基于此，本文提出一种综合利用签名字形和书写力特征的在线签名认证方法.首先，利用一种新型的FTablet手写板用于获取签名的动态笔迹和书写力信息，并根据速度极小值点对签名进行笔画分段.然后从中提取16维的字形和书写力特征矢量序列用于签名隐马尔可夫模型(HMM)的建立和认证.在基于FTablet手写板建立的签名数据库上的认证实验结果表明书写力特征比字形特征更难以模仿，两种特征相结合可以有效提高系统的识别性能，提出的认证方法的相等错误率(EER)达到3.9%.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孟明
	吴仲城
	余永
	葛运建

关键词 ：在线签名认证, 隐马尔可夫模型(HMM), 笔画分段, 书写力

Abstract：Writing forces of signature contain a great many individual characteristics, but in current online handwritten signature verification systems this information is often utilized deficiently because of the limitation of the existing input device. In this paper, an online signature verification algorithm using the shape features and the force features is presented. The dynamic trajectory and the writing force of signature are captured by a novel digital tablet, namely FTablet. Each signature is segmented according to its minimum velocity points. Then a 16dimensional vector of shape and force features is extracted for each segment. The resulting sequence is used for training a HMM to achieve signature verification. The experimental results on our database show that the force feature is more difficult to forge than the shape feature and the combination of the two features can effectively improve the performance. The proposed algorithm has achieved equal error rate (EER) of 3.9%.

Key words： Online Signature Verification Hidden Markov Model (HMM) Stroke Segmentation Writing Force

收稿日期: 2005-12-30

ZTFLH:

TP391.4

基金资助:国家自然科学基金资助项目(No.60475005,No.60575058)

作者简介: 孟明，男，1975年生，博士，主要研究方向为生物特征识别、信息获取与处理等.Email:emnming@yahoo.com.cn.吴仲城，男，1968年生，博士，主要研究方向为人机接触交互、仿生机器人传感网络等.余永，男，1957年生，研究员，博士生导师，主要研究方向为智能机器人传感与控制、人机接触交互等.葛运建，男，1947年生，研究员，博士生导师，主要研究方向为智能机器人传感与控制、信息获取与处理等.

引用本文:

孟明，吴仲城，余永，葛运建. 基于笔段特征和HMM的在线签名认证方法研究^*[J]. 模式识别与人工智能, 2007, 20(1): 95-100. MENG Ming , WU ZhongCheng , YU Yong , GE YunJian. Online Signature Verification Based on Segment Features and HMM. , 2007, 20(1): 95-100.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/ 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2007/V20/I1/95

[1] Plamondon R, Lorette G. Automatic Signature Verification and Writer Identification-the State of the Art. Pattern Recognition, 1989, 22(2):107131
[2] Dimauro G, Impedovo S, Lucchese M G, et al. Recent Advancements in Automatic Signature Verification // Proc of the 9th International Workshop on Frontiers in Handwriting Recognition. Tokyo, Japan, 2004: 179184
[3] Parizeau M, Plamondon R. A Comparative Analysis of Regional Correlation, Dynamic Time Warping, and Skeletal Tree Matching for Signature Verification. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12(7): 710717
[4] Martens R, Claesen L. OnLine Signature Verification by Dynamic Time Warping // Proc of the 13th International Conference on Pattern Recognition. Vienna, Austria, 1996, Ⅲ: 3842
[5] Yang L, Widjaja B K, Prasad R. Application of Hidden Markov Models for Signature Verification. Pattern Recognition, 1995, 28(2): 161170
[6] Dolfing J, Aarts E, Oosterhout J J G M. OnLine Signature Verification with Hidden Markov Models // Proc of the 14th International Conference on Pattern Recognition. Brisbane, Australia, 1998, Ⅱ: 13091312
[7] Shafiei M M, Rabiee H R. A New Online 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
[8] 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. 一个基于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)
[9] Crane H D, Ostrem J S. Automatic Signature Verification Using a ThreeAxis ForceSensitive Pen. IEEE Trans on Systems, Man, and Cybernetics, 1983, 13(3):329337
[10] Ohishi T, Komiya Y, Matsumoto T. OnLine Signature Verification Using PenPosition, PenPressure and PenInclination Trajectories // Proc of the 15th International Conference on Pattern Recognition. Barcelona, Spain, 2000, Ⅳ: 547550
[11] Sato Y, Kogure K. OnLine Signature Verification Based on Shape, Motion and Writing Pressure // Proc of the 6th IEEE International Conference on Pattern Recognition. Munich, Germany, 1982: 823826
[12] Fang Ping, Wu Zhongcheng, Meng Ming, et al. A Novel Tablet for OnLine Handwriting Signal Capture // Proc of the 5th World Congress on Intelligent Control and Automation. Hangzhou, China, 2004, Ⅵ: 37143717
[13] Nalwa V S. Automatic OnLine Signature Verification. Proc of the IEEE, 1997, 85(2): 215239
[14] Brault J T, Plamondon R. Segmenting Handwritten Signature at Their Perceptually Important Points. IEEE Trans on Pattern Analysis and Machine Intelligence, 1993, 15(9): 953957
[15] Yue K W, Wijesoma W S. Improved Segmentation and Segment Association for OnLine Signature Verification // Proc of the IEEE International Conference on Systems, Man, and Cybernetics. New York, USA, 2000: 27522756
[16] Plamondon R, Guerfali W. Why Handwriting Segmentation Can Be Misleading? // Proc of the 13th International Conference on Pattern Recognition. Vienna, Austria, 1996, Ⅳ: 396400
[17] Rabiner L R. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proc of the IEEE, 1989, 77(2): 257286