基于特征向量和分类树的签名认证方法

Signature Verification Based on Feature Vectors and Clustering Trees

本文介绍了如何从签名的基本信息中提取签名特征构成特征向量 ,在此基础上提出了生成分类树 ,以及根据分类树的树型特征进行签名真伪认证的方法。该方法简单快捷 ,决策依据的物理意义明确 ,在实验中获得了较好的认证效果。

This paper describes how to extract features from the basic information of signatures. Based on feature vectors, a clustering tree is generated. The shape of the clustering tree is then analyzed to decide whether the signature being verified is genuine or false. This method is simple but effective, and its physical meaning is clear. A good result is obtained in the experiment of signature verification.