Exploring Transformers for On-Line Handwritten Signature Verification

TL;DR

This paper explores the use of Transformer-based architectures for on-line handwritten signature verification, demonstrating promising results and suggesting their suitability for biometric authentication tasks.

Contribution

It investigates four Transformer configurations, adapting architectures from gait and activity recognition to improve signature verification performance.

Findings

Transformers outperform traditional methods in signature verification.

Two configurations based on Vanilla Transformer encoder show strong results.

Experimental results are promising and support further research in this area.

Abstract

The application of mobile biometrics as a user-friendly authentication method has increased in the last years. Recent studies have proposed novel behavioral biometric recognition systems based on Transformers, which currently outperform the state of the art in several application scenarios. On-line handwritten signature verification aims to verify the identity of subjects, based on their biometric signatures acquired using electronic devices such as tablets or smartphones. This paper investigates the suitability of architectures based on recent Transformers for on-line signature verification. In particular, four different configurations are studied, two of them rely on the Vanilla Transformer encoder, and the two others have been successfully applied to the tasks of gait and activity recognition. We evaluate the four proposed configurations according to the experimental protocol proposed in the SVC-onGoing competition. The results obtained in our experiments are promising, and promote the use of Transformers for on-line signature verification.