Robust Few-Shot Online Signature Verification via Bi-Directional-Guided Fusion and Padding-Aware Attention
Inventions · 28.07.2026 · 11 (4) · 78
DOI: 10.3390/inventions11040078 ↗Kurz gefasst
Fachartikel in der Zeitschrift Inventions, online erschienen am 28.07.2026. Verfasst von Liyan Huang und 2 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Funds for the Innovation of Policing Science and Technology, Fujian Province.
Abstract (Originalsprache)
Online signature verification (OSV) remains challenging under few-shot enrollment and multi-posture conditions, where limited reference samples and writing variations increase intra-writer variability and degrade verification performance. Existing methods often rely on simple feature concatenation and insufficiently exploit interactions between global statistical and temporal dynamic representations, while attention mechanisms in variable-length sequences may be affected by invalid padded regions. To address these limitations, this study introduces FT-Transformer, a hybrid CNN–Transformer framework for few-shot online signature verification. The model jointly encodes 18-dimensional local dynamic descriptors and 51-dimensional global statistical features. A bi-directional-guided fusion mechanism is introduced to facilitate interaction between heterogeneous representations, while a closed-loop feedback pathway and padding-aware attention masking are incorporated to improve feature robustness. Experiments on the public SVC2004 benchmark and a custom multi-posture dataset (MPIS-Sig) evaluate the performance of this framework. Under the WD-10/10 protocol, FT-Transformer achieves an Equal Error Rate (EER) of 0.16% on SVC2004 Task 2 and maintains an EER of 2.40% under the more challenging WD-5/5 setting. On MPIS-Sig, the model achieves over 98% verification accuracy across different writing postures. These results demonstrate that FT-Transformer effectively improves OSV robustness under data-scarce and multi-posture conditions.
Förderung
- Funds for the Innovation of Policing Science and Technology, Fujian Province
Zitieren
APA
Huang, L., Ruan, Y., & Li, W. (2026). Robust Few-Shot Online Signature Verification via Bi-Directional-Guided Fusion and Padding-Aware Attention. Inventions, 11(4), 78. https://doi.org/10.3390/inventions11040078
Vancouver
Huang L, Ruan Y, Li W. Robust Few-Shot Online Signature Verification via Bi-Directional-Guided Fusion and Padding-Aware Attention. Inventions. 2026;11(4):78. doi:10.3390/inventions11040078
BibTeX
@article{Huang2026,
author = {Huang, Liyan and Ruan, Yuanxiang and Li, Weijun},
title = {Robust Few-Shot Online Signature Verification via Bi-Directional-Guided Fusion and Padding-Aware Attention},
journal = {Inventions},
year = {2026},
volume = {11},
number = {4},
pages = {78},
doi = {10.3390/inventions11040078}
}
EUVIMED