Signature verification improves using augmented path signatures and new model
Online Signature Verification Using Augmented Path Signature and T-Mamba
Machine LearningComputer Vision and Pattern Recognition
Summary
Checking if a signature is real or fake is important for security in banks and businesses. The authors found that existing computer methods sometimes miss important details in how a signature changes over time. They combined a special math tool called an augmented path signature with a new type of model called T-Mamba that looks at short and long parts of a signature. Their approach works better than previous ones, especially when there isn’t much training data available.
What this means in practice
- •For banking security teams: Integrate improved signature verification into authentication systems to reduce fraud with limited signature samples.$Commercial implications: This paper enables more accurate and robust signature verification products for financial institutions, enhancing security and lowering fraud risks.
- •For software developers: Develop apps needing user identity checks via signatures using enhanced models that handle temporal patterns and long-range data dependencies.
Authors
Ruiling Li, Danyu Yang
Abstract
Handwritten signature verification is vital for personal authentication across commercial and financial applications. Although deep learning methods are widely adopted for online signature verification (OSV), they often struggle with capturing highly discriminative features and modelling long-range dependencies. To address these issues, we propose a novel framework that integrates the augmented path signature (APS) descriptor with the T-Mamba model. The APS descriptor first applies time and basepoint augmentations, then computes sliding-window path signatures. The path signature is a non-parametric feature map from rough path theory that effectively captures geometric structures and nonlinear inter-channel interactions. Inspired by the efficacy of state space models (SSMs) in sequence modelling, our T-Mamba model employs a hybrid design combining two temporal convolutional network (TCN) blocks with a time-scanning Mamba. This design enables the model to learn both local temporal patterns and global long-range dependencies, substantially improving verification accuracy. Our framework achieves state-of-the-art EERs on three public benchmark datasets (MCYT-100, SVC-2004 Task 2, DeepSignDB), validating its effectiveness and robustness, especially when the training data is limited. Our code is publicly available at https://github.com/DLRL04/OSV-using-APS-and-T-Mamba.