发表机构
College of Mathematics and Statistics, Chongqing University（重庆大学数学与统计学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出结合增强路径签名与T-Mamba的在线签名验证框架，解决特征判别性和长距离依赖问题，在三个基准数据集上达到最先进性能。
AI 中文摘要
手写签名验证对于商业和金融应用中的个人认证至关重要。尽管深度学习方法被广泛用于在线签名验证（OSV），但它们通常难以捕捉高度判别性的特征并建模长距离依赖。为解决这些问题，我们提出了一种新颖的框架，将增强路径签名（APS）描述符与T-Mamba模型相结合。APS描述符首先应用时间和基点增强，然后计算滑动窗口路径签名。路径签名是粗糙路径理论中的一种非参数特征映射，能有效捕捉几何结构和非线性通道间交互。受状态空间模型（SSMs）在序列建模中有效性的启发，我们的T-Mamba模型采用混合设计，结合两个时间卷积网络（TCN）块与时间扫描Mamba。这种设计使模型能够学习局部时间模式和全局长距离依赖，显著提高验证准确性。我们的框架在三个公开基准数据集（MCYT-100、SVC-2004 Task 2、DeepSignDB）上实现了最先进的等错误率（EERs），验证了其有效性和鲁棒性，尤其是在训练数据有限的情况下。我们的代码在此https URL公开可用。
英文摘要
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.
CommentsInternational Conference on Document Analysis and Recognition (ICDAR) 2026
DOI：10.1007/978-3-032-36042-7_8
