Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature

TL;DR

This paper introduces a novel RNN-based system combined with a new length-normalized path signature descriptor to enhance online signature verification, achieving state-of-the-art results on a public dataset.

Contribution

The paper presents a new RNN training approach for signature verification and proposes the LNPS descriptor with invariance properties, improving verification accuracy.

Findings

Achieved 2.37% EER on SVC-2004 dataset.

Demonstrated the effectiveness of LNPS in invariance and verification.

Produced discriminative features through end-to-end RNN training.

Abstract

Inspired by the great success of recurrent neural networks (RNNs) in sequential modeling, we introduce a novel RNN system to improve the performance of online signature verification. The training objective is to directly minimize intra-class variations and to push the distances between skilled forgeries and genuine samples above a given threshold. By back-propagating the training signals, our RNN network produced discriminative features with desired metrics. Additionally, we propose a novel descriptor, called the length-normalized path signature (LNPS), and apply it to online signature verification. LNPS has interesting properties, such as scale invariance and rotation invariance after linear combination, and shows promising results in online signature verification. Experiments on the publicly available SVC-2004 dataset yielded state-of-the-art performance of 2.37% equal error rate (EER).