Modified Dynamic Time Warping with Local and Global Weighting for Online Signature Verification

This study proposes a novel online signature verification using locally and globally weighted dynamic time warping (LG-DTW) to improve the verification performance. In the enrollment phase, we obtain a mean template set among references using Euclidean barycenter-based DTW barycenter averaging. We acquire a local weighting estimate obtained by analyzing direct matching points between the mean template and reference sets for intra-user variability. We compute a global weighting estimate using gradient boosting for inter-user variability. Finally, in the verification phase, we apply the local and global weighting estimates to acquire a discriminative LG-DTW between a query sample and the mean template set. Experimental results obtained on the public SVC2004 Task2 dataset confirmed the effectiveness of the proposed method.

Automated summary

This study proposes a novel online signature verification method using locally and globally weighted dynamic time warping (LG-DTW) to improve verification performance. The method utilizes Euclidean barycenter-based DTW barycenter averaging in the enrollment phase to obtain a mean template set and employs local and global weighting estimates to handle intra-user and inter-user variability. Experimental results confirm the effectiveness of the proposed method.