Meta-learning for fast classifier adaptation to new users of Signature Verification systems

TL;DR

This paper introduces a meta-learning approach for offline handwritten signature verification, enabling rapid adaptation to new users with minimal genuine signatures and improved discrimination against skilled forgeries.

Contribution

It proposes a novel meta-learning framework that guides classifier adaptation for each user using only genuine signatures, enhancing verification performance with few samples.

Findings

Outperforms writer-independent systems in experiments.

Achieves comparable results to state-of-the-art writer-dependent systems with few samples.

Effective in discriminating skilled forgeries even without training on them.

Abstract

Offline Handwritten Signature verification presents a challenging Pattern Recognition problem, where only knowledge of the positive class is available for training. While classifiers have access to a few genuine signatures for training, during generalization they also need to discriminate forgeries. This is particularly challenging for skilled forgeries, where a forger practices imitating the user's signature, and often is able to create forgeries visually close to the original signatures. Most work in the literature address this issue by training for a surrogate objective: discriminating genuine signatures of a user and random forgeries (signatures from other users). In this work, we propose a solution for this problem based on meta-learning, where there are two levels of learning: a task-level (where a task is to learn a classifier for a given user) and a meta-level (learning across tasks). In particular, the meta-learner guides the adaptation (learning) of a classifier for each user, which is a lightweight operation that only requires genuine signatures. The meta-learning procedure learns what is common for the classification across different users. In a scenario where skilled forgeries from a subset of users are available, the meta-learner can guide classifiers to be discriminative of skilled forgeries even if the classifiers themselves do not use skilled forgeries for learning. Experiments conducted on the GPDS-960 dataset show improved performance compared to Writer-Independent systems, and achieve results comparable to state-of-the-art Writer-Dependent systems in the regime of few samples per user (5 reference signatures).