姓名字在线签名与非签名书写的可区分性研究  

Distinguish research of name character writing in signature and non-signature

作　　者：刘蕾[1] 段会川[1] 

机构地区：[1]山东师范大学信息科学与工程学院,山东济南250014

出　　处：《计算机工程与设计》2009年第21期5016-5018,5021,共4页Computer Engineering and Design

摘　　要：对姓名字在线签名与非签名书写的区别进行了研究。采集了多位实验者姓名字的在线签名的书写数据和混于文本中的书写数据,将这两组数据看成是两个类,采用动态时间规整(DTW)算法,以位移信号作为特征向量,计算了两个类的类内距离和类间距离。得到姓名字在线签名写法的差别小于非签名写法的差别小于签名字与非签名字之间写法的差别。实验结果表明,该方法具有较强的稳定性和识别性能好的优点。The distinction between name character in signature and non-signature is researched. It collected the names of a number of experimenters＇ written data about on-line signatures and data which mixed in the text. The two sets of data are considered as two categories, dynamic time warping （DTW） algorithm is adopted to shift displacement signal as a feature vector to study the distinction of the names of characters about on-line signatures and non-written signatures and to calculate the distance between two types of class and category distance. The results show that the names of characters on-line signature difference is less than the non-written signature and also less than the difference between the signature characters and non-written signatures. Experiments also demonstrate that the approach has high stability and recognition performance.

关 键 词：动态时间规整 姓名字 在线签名 非签名 写法差别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]