GAFSV-Net: A Vision Framework for Online Signature Verification

TL;DR

GAFSV-Net introduces a 2D image-based approach for online signature verification, leveraging Gramian Angular Fields and dual-branch encoders to improve accuracy over sequence-based methods.

Contribution

It proposes a novel 2D temporal encoding method using GAFs and a dual-branch ConvNeXt encoder with cross-attention for enhanced signature verification.

Findings

Outperforms sequence-based baselines on DeepSignDB and BiosecurID datasets.

Demonstrates the effectiveness of 2D temporal encoding independent of training procedures.

Ablation studies highlight the importance of each design component.

Abstract

Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few enrollment samples. Existing deep learning methods operate directly on raw temporal sequences, restricting them to 1D architectures and preventing the use of pretrained 2D vision backbones. We bridge this gap with GAFSV-Net, which represents each signature as a six-channel asymmetric Gramian Angular Field image: three kinematic channels (pen speed, pressure derivative, direction angle) are each encoded into complementary GASF and GADF matrices that capture pairwise temporal co-occurrence and directional transition structure respectively. A dual-branch ConvNeXt-Tiny encoder processes GASF and GADF independently, with bidirectional cross-attention enabling each branch to query discriminative patterns from the other before metric-space projection. Training uses semi-hard triplet loss with skilled-forgery hard-negative injection; verification is performed via cosine similarity against a small enrollment prototype. We evaluate on DeepSignDB and BiosecurID, outperforming all sequence-based baselines trained under identical objectives, demonstrating that the representational gain of 2D temporal encoding is consistent and independent of training procedure, with ablations characterising each design choice's contribution.