Writer-independent online signature verification based on 2D representation of time series data using triplet supervised network

Abstract

Online signature verification (OSV) as a critical link of the paperless office still has tremendous challenges. In this paper, we propose a novel Writer-Independent (WI) OSV framework that includes three parts. (1) The two-dimensional (2D) representation method is designed to transform the original time-series signature data into stroke images with dynamic-static hybrid information. (2) The Channel-wise Weight Learning (CWL) mechanism is integrated into the feature extractor to mine the potential relationship between three dynamic attributes (altitude, azimuth, and pressure). (3) A new Triplet Supervised Network (TSN) that contains three weight-shared convolution neural network (CNN) streams was provided to measure the distance of [Anchor, Positive, Test]. The experimental results show that our model has at least 1.29% accuracy improvement when confronted with skilled forgery signatures than that of other classical CNNs and 11.43% than lightweight models. Moreover, the TSN model is superior to the previous OSV algorithms in the WI pattern.