Learning Features for Offline Handwritten Signature Verification using Deep Convolutional Neural Networks

Abstract

Verifying the identity of a person using handwritten signatures is challenging in the presence of skilled forgeries, where a forger has access to a person's signature and deliberately attempt to imitate it. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish genuine signatures and skilled forgeries. This reflects in a relatively poor performance, with verification errors around 7% in the best systems in the literature. To address both the difficulty of obtaining good features, as well as improve system performance, we propose learning the representations from signature images, in a Writer-Independent format, using Convolutional Neural Networks. In particular, we propose a novel formulation of the problem that includes knowledge of skilled forgeries from a subset of users in the feature learning process, that aims to capture visual cues that distinguish genuine signatures and forgeries regardless of the user. Extensive experiments were conducted on four datasets: GPDS, MCYT, CEDAR and Brazilian PUC-PR datasets. On GPDS-160, we obtained a large improvement in state-of-the-art performance, achieving 1.72% Equal Error Rate, compared to 6.97% in the literature. We also verified that the features generalize beyond the GPDS dataset, surpassing the state-of-the-art performance in the other datasets, without requiring the representation to be fine-tuned to each particular dataset.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Offline Handwritten Signature Verification - Literature Review
• Writer-independent Feature Learning for Offline Signature Verification using Deep Convolutional Neural Networks
• Deep Learning of Representations: Looking Forward
• Analyzing features learned for Offline Signature Verification using Deep CNNs

Cited by in corpus (22)

• A Perspective Analysis of Handwritten Signature Technology
• Offline Handwritten Signature Verification - Literature Review
• Fixed-sized representation learning from Offline Handwritten Signatures of different sizes
• Multi-Representational Learning for Offline Signature Verification using Multi-Loss Snapshot Ensemble of CNNs
• Characterizing and evaluating adversarial examples for Offline Handwritten Signature Verification
• Signature Verification using Geometrical Features and Artificial Neural Network Classifier
• Learning sound representations using trainable COPE feature extractors
• Attention based Writer Independent Handwriting Verification
• Learning Representations from Persian Handwriting for Offline Signature Verification, a Deep Transfer Learning Approach
• Explainable offline automatic signature verifier to support forensic handwriting examiners
• Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks
• Investigating the Common Authorship of Signatures by Off-Line Automatic Signature Verification Without the Use of Reference Signatures
• Offline handwritten mathematical symbol recognition utilising deep learning
• Graph-Based Offline Signature Verification
• Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess
• Active Transfer Learning for Persian Offline Signature Verification
• Persian Signature Verification using Fully Convolutional Networks
• Brain inspired neuronal silencing mechanism to enable reliable sequence identification
• MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
• FCN+RL: A Fully Convolutional Network followed by Refinement Layers to Offline Handwritten Signature Segmentation
• Character-independent font identification
• A comprehensive study of sparse representation techniques for offline signature verification