Time-series averaging and local stability-weighted dynamic time warping for online signature verification

作者：

Highlights：

• We propose a novel single-template matching method for online signature verification.

• The single-template strategy adopts a mean template set and LS-DTW.

• The mean template is created by a recent time-series averaging method, EB-DBA.

• The LS-DTW is calculated by incorporating the local stability when matching two signatures.

• The proposed method achieves higher performance than existing signature verification systems.

摘要

•We propose a novel single-template matching method for online signature verification.•The single-template strategy adopts a mean template set and LS-DTW.•The mean template is created by a recent time-series averaging method, EB-DBA.•The LS-DTW is calculated by incorporating the local stability when matching two signatures.•The proposed method achieves higher performance than existing signature verification systems.

论文关键词：Biometrics,Signature verification,In-air signature,Time-series analysis,Dynamic time warping (DTW),Euclidean barycenter-based DTW barycenter averaging (EB-DBA),Local stability-weighted DTW (LS-DTW)

论文评审过程：Received 14 April 2020, Revised 13 September 2020, Accepted 13 October 2020, Available online 14 October 2020, Version of Record 30 January 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107699