# Catch Me If You Can

## TL;DR

This paper explores using Variational Auto-Encoders to distinguish genuine signatures by learning a latent space, analyzing their effectiveness and potential for ensemble methods in signature verification.

## Contribution

Introduces a VAE-based approach for signature verification that leverages latent space representations and classifier integration, with analysis of disentanglement and posterior collapse.

## Key findings

- Method performs less well than existing approaches
- VAE latent space can distinguish genuine signatures
- Potential for ensemble use in future models

## Abstract

As advances in signature recognition have reached a new plateau of performance at around 2% error rate, it is interesting to investigate alternative approaches. The approach detailed in this paper looks at using Variational Auto-Encoders (VAEs) to learn a latent space representation of genuine signatures. This is then used to pass unlabelled signatures such that only the genuine ones will successfully be reconstructed by the VAE. This latent space representation and the reconstruction loss is subsequently used by random forest and kNN classifiers for prediction. Subsequently, VAE disentanglement and the possibility of posterior collapse are ascertained and analysed. The final results suggest that while this method performs less well than existing alternatives, further work may allow this to be used as part of an ensemble for future models.