基于HMM/DTW两级结构的签名认证方法  

Signature Verification Algorithm Based on HMM/DTW Two-Level Architecture

作　　者：于宏斌[1] 吴仲城[1,2] 申飞[1,2] 

机构地区：[1]中国科学院合肥智能机械研究所仿生感知与控制研究中心,合肥230031 [2]中国科学院强磁场科学中心控制组,合肥230031

出　　处：《模式识别与人工智能》2010年第1期107-114,共8页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金资助项目(No.60975057)

摘　　要：提出一种基于HMM和DTW在线手写签名认证方法的改进方法.该方法使用签名关键点和关键点的特征值进行签名的状态划分和状态匹配,实现类内签名状态划分的一致性.并利用在线手写签名二维信息的DTW距离作为签名隐马尔科夫模型的状态观测值,构建二级签名隐马尔科夫模型认证框架进行签名认证,得到较好的认证效果.实验结果表明,认证的准确率能达到93%左右.A method for online hand-writing signature verification is proposed based on hidden Markov model （HMM） combined with dynamic time wrapping （DTW）. To satisfy the inter-class consistency of signature segmentation and status division, the critical points in signatures are defined and its features are calculated. The difference values measured by DTW using two-dimension signature shape are used as observations of HMM to build the two-level architecture of HMMs for handwriting signature verification. The accuracy rate reaches about 93%.

关 键 词：在线签名认证 动态规整(DTW) 隐马尔科夫模型(HMM) 签名分段 

分 类 号：TN918.1[电子电信—通信与信息系统]