Writer-independent Feature Learning for Offline Signature Verification using Deep Convolutional Neural Networks

TL;DR

This paper introduces a writer-independent feature learning approach using deep convolutional neural networks for offline signature verification, achieving high accuracy across multiple datasets and surpassing existing methods.

Contribution

It presents a novel deep learning-based feature extraction method that generalizes across writers and datasets, improving verification performance over traditional handcrafted features.

Findings

Achieved near state-of-the-art results on GPDS-960 dataset.

Improved verification accuracy on Brazilian PUC-PR dataset.

Features learned are discriminative across different datasets.

Abstract

Automatic Offline Handwritten Signature Verification has been researched over the last few decades from several perspectives, using insights from graphology, computer vision, signal processing, among others. In spite of the advancements on the field, building classifiers that can separate between genuine signatures and skilled forgeries (forgeries made targeting a particular signature) is still hard. We propose approaching the problem from a feature learning perspective. Our hypothesis is that, in the absence of a good model of the data generation process, it is better to learn the features from data, instead of using hand-crafted features that have no resemblance to the signature generation process. To this end, we use Deep Convolutional Neural Networks to learn features in a writer-independent format, and use this model to obtain a feature representation on another set of users, where we train writer-dependent classifiers. We tested our method in two datasets: GPDS-960 and Brazilian PUC-PR. Our experimental results show that the features learned in a subset of the users are discriminative for the other users, including across different datasets, reaching close to the state-of-the-art in the GPDS dataset, and improving the state-of-the-art in the Brazilian PUC-PR dataset.