Analyzing features learned for Offline Signature Verification using Deep CNNs

TL;DR

This paper improves deep CNN-based features for offline signature verification, achieving state-of-the-art accuracy on the GPDS dataset by exploring various architectures and analyzing learned features.

Contribution

It advances the performance of data-driven, writer-independent CNN models for signature verification and provides insights into the learned feature space and error patterns.

Findings

Achieved an EER of 2.74% on GPDS-160, outperforming previous methods.

Deep CNNs effectively distinguish signatures with different global appearances.

Vulnerable to forgeries closely mimicking genuine signatures, especially slow tracings.

Abstract

Research on Offline Handwritten Signature Verification explored a large variety of handcrafted feature extractors, ranging from graphology, texture descriptors to interest points. In spite of advancements in the last decades, performance of such systems is still far from optimal when we test the systems against skilled forgeries - signature forgeries that target a particular individual. In previous research, we proposed a formulation of the problem to learn features from data (signature images) in a Writer-Independent format, using Deep Convolutional Neural Networks (CNNs), seeking to improve performance on the task. In this research, we push further the performance of such method, exploring a range of architectures, and obtaining a large improvement in state-of-the-art performance on the GPDS dataset, the largest publicly available dataset on the task. In the GPDS-160 dataset, we obtained an Equal Error Rate of 2.74%, compared to 6.97% in the best result published in literature (that used a combination of multiple classifiers). We also present a visual analysis of the feature space learned by the model, and an analysis of the errors made by the classifier. Our analysis shows that the model is very effective in separating signatures that have a different global appearance, while being particularly vulnerable to forgeries that very closely resemble genuine signatures, even if their line quality is bad, which is the case of slowly-traced forgeries.