基于几何中心静态手写签名的识别算法研究

Center based off-line signature verification

研究了静态手写体签名识别和认证的问题。针对静态手写体签名无法提供笔画之间前后时序动态信息和手写笔画的压力信息,提出了一种利用手写签名的几何中心作为特征值的识别和认证算法。首先将静态签名图像依据几何中心不断进行切分,使其成为独立的小块;然后依据各个小块的几何中心的相对位置和距离提取特征值;在此基础上进行签名识别和认证。实验结果显示本方法快速有效,所提取的特征能稳定地描述包含集合形变的手写签名字体。该方法能拓展应用到手写体的识别系统中。

This paper proposed a new approach for signature verification of off-line signatures based on relative distances be, tween centroids. Distances betwee.n centroids of off-line signatures were used to form an interval valued symbolic feature vector for representing signatures. It investigated the feasibility of the proposed representation scheme for signature verification on a public data set, and clustered similar signatures in each class and also investigated the cluster based symbolic representation for signature verification. Unlike other signature verification methods ,the proposed method is simple and efficient. Several experiments are conducted to demonstrate the efficacy of the proposed scheme.