Jia Yu, Huang Linlin, Chen Houjin
School of Electronic and Information Engineering, Beijing Jiaotong University, No. 3 Shangyuancun Haidian District, Beijing 100044, China.
Sensors (Basel). 2019 Apr 16;19(8):1808. doi: 10.3390/s19081808.
As a behavioral biometric trait, an online signature is extensively used to verify a person's identity in many applications. In this paper, we present a method using shape contexts and function features as well as a two-stage strategy for accurate online signature verification. Specifically, in the first stage, features of shape contexts are extracted from the input and classification is made based on distance metric. Only the inputs passing by the first stage are represented by a set of function features and verified. To improve the matching accuracy and efficiency, we propose shape context-dynamic time warping (SC-DTW) to compare the test signature with the enrolled reference ones based on the extracted function features. Then, classification based on interval-valued symbolic representation is employed to decide if the test signature is a genuine one. The proposed method is evaluated on SVC2004 Task 2 achieving an Equal Error Rate of 2.39% which is competitive to the state-of-the-art approaches. The experiment results demonstrate the effectiveness of the proposed method.
作为一种行为生物特征，在线签名在许多应用中被广泛用于验证个人身份。在本文中，我们提出了一种使用形状上下文和功能特征以及两阶段策略的方法，用于准确的在线签名验证。具体而言，在第一阶段，从输入中提取形状上下文特征，并基于距离度量进行分类。只有通过第一阶段的输入才由一组功能特征表示并进行验证。为了提高匹配精度和效率，我们提出了形状上下文-动态时间规整（SC-DTW），以基于提取的功能特征将测试签名与注册的参考签名进行比较。然后，采用基于区间值符号表示的分类来确定测试签名是否为真实签名。所提出的方法在SVC2004任务2上进行了评估，获得了2.39%的等错误率，与当前的先进方法具有竞争力。实验结果证明了所提出方法的有效性。
