《计算机应用研究》|Application Research of Computers

基于时序特征融合的动态签名鉴伪算法

Dynamic signature verification method based on timing feature fusion

免费全文下载 (已被下载 次)  
获取PDF全文
作者 李佳,李庆武,马云鹏,丁惠洋
机构 河海大学 a.物联网工程学院;b.常州市传感网与环境感知重点实验室,江苏 常州 213022
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)07-022-2032-05
DOI 10.19734/j.issn.1001-3695.2019.01.0011
摘要 针对现有签名鉴伪方法对高水平伪签名鉴伪准确率低的问题,提出一种基于时序特征融合的动态签名鉴伪算法。首先根据签名者落笔与提笔的时间节点建立动态时间轴,在签名过程中提取笔迹的压力和笔速两类时序特征;然后在两类特征对应数据的基础上构建时序特征融合模型,通过一种多维空间模型相似性度量方法计算待测签名和样本签名的相似度,从而实现签名真伪性鉴别。实验结果表明,与现有算法相比,该方法进一步提高了签名鉴伪的准确率和通用性。
关键词 签名鉴伪; 时序特征; 特征融合模型; 相似性度量
基金项目 国家自然科学基金资助项目(F030403)
江苏省重点研发计划资助项目(BE2017057)
本文URL http://www.arocmag.com/article/01-2020-07-022.html
英文标题 Dynamic signature verification method based on timing feature fusion
作者英文名 Li Jia, Li Qingwu, Ma Yunpeng, Ding Huiyang
机构英文名 a.College of Internet of Things Engineering,b.Changzhou Key Laboratory of Sensor Networks & Environment Sensing,Hohai University,Chang-zhou Jiangsu 213022,China
英文摘要 In order to increase the accuracy rate of signature verification for higher-level forgery, this paper developed a dynamic signature verification method based on timing feature fusion. First, during the writing process, it created a dynamic timeline, and extracted two timing features, the handwriting pressure and writing speed. Then it designed a fusion model of timing features based on the data of the features above. This paper calculated the similarity between the test signature and the sample signature by a similarity measure method of multidimensional spatial model. Finally, it realized signature verification by the analysis of similarity. The experiments show that the proposed algorithm has the advantages of high accuracy rate and good universality.
英文关键词 signature verification; timing feature; feature fusion model; similarity measure
参考文献 查看稿件参考文献
 
收稿日期 2019/1/20
修回日期 2019/3/11
页码 2032-2036
中图分类号 TP301.6
文献标志码 A