Meta-learning for fast classifier adaptation to new users of Signature Verification systems
This work addresses the challenge of verifying signatures against skilled forgeries in biometric security systems, offering a solution that is incremental by building on meta-learning techniques for user-specific adaptation.
The paper tackles the problem of offline handwritten signature verification, where classifiers must discriminate skilled forgeries using only genuine signatures for training, by proposing a meta-learning approach that guides classifier adaptation for each user. Experiments on the GPDS-960 dataset show improved performance over writer-independent systems and results comparable to state-of-the-art writer-dependent systems with only 5 reference signatures per user.
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).