On-line signature verification using improved segmentation

被引:0
作者
Zou, MF [1 ]
Tong, JJ [1 ]
Lou, ZL [1 ]
Liu, CP [1 ]
机构
[1] Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China
来源
2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS | 2003年
关键词
signatures verification; biometric authentication; hidden Markov model; segmentation;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper describes an on-line signature verification using HMM (Hidden Markov Model). The system is based on combining local time-based and shape-based comparison between the input signature and the reference model. We proposed a novel initialization algorithm to avoid the local optimal of the HMM's re-estimation. To get reliable segment using HMM, we adopt a meliorated HMM re-estimation algorithm during training. In addition, we use a novel algorithm to avoid losing the important information at cusps in preprocessing. The tests based on databases and in live reveal the feasibility of the proposed method.
引用
收藏
页码:256 / 261
页数:6
相关论文
共 18 条
[11]  
Ma MM, 2000, 2000 CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, CONFERENCE PROCEEDINGS, VOLS 1 AND 2, P890, DOI 10.1109/CCECE.2000.849594
[12]  
OHISHI T, 2000, ICPR 00, V4
[13]  
PLAMONDON R, 1996, P ICPR 96, V3, P396
[14]  
RHEE TH, LINE SIGNATURE VERIF
[15]  
Rigoll Gerhard, 1999, ADV HANDWRITING RECO, P69
[16]   Off-line signature verification by local granulometric size distributions [J].
Sabourin, R ;
Genest, G ;
Preteux, FJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (09) :976-988
[17]  
YUE KW, 2000, 2000 IEEE INT C, P4
[18]  
ZOU MF, 2002, CACSUK, P390