From text to signatures: Knowledge transfer for efficient deep feature learning in offline signature verification

D Tsourounis, I Theodorakopoulos, EN Zois… - Expert Systems with …, 2022 - Elsevier
Handwritten signature is a common biometric trait, widely used for confirming the presence
or the consent of a person. Offline Signature Verification (OSV) is the task of verifying the …

Learning the micro deformations by max-pooling for offline signature verification

Y Zheng, BK Iwana, MI Malik, S Ahmed, W Ohyama… - Pattern Recognition, 2021 - Elsevier
For signature verification systems, micro deformations can be defined as the small
differences in the same strokes of signatures or special writing habits of different signers …

A multi-task approach for contrastive learning of handwritten signature feature representations

TB Viana, VLF Souza, ALI Oliveira, RMO Cruz… - Expert Systems with …, 2023 - Elsevier
In spite of recent advances in computer vision, the classic problem of offline handwritten
signature verification still remains challenging. The signature verification task has a high …

AVN: An adversarial variation network model for handwritten signature verification

H Li, P Wei, P Hu - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
Handwritten signature verification is a crucial yet challenging problem. While previous
studies have made great progress in this problem, they learn signature features passively …

Subscripto multiplex: A Riemannian symmetric positive definite strategy for offline signature verification

EN Zois, S Said, D Tsourounis, A Alexandridis - Pattern Recognition Letters, 2023 - Elsevier
The human handwritten signature is considered to be a significant biometric trait. In the case
of offline signatures, the problem is addressed as an image recognition task. On the other …

Sequential motif profiles and topological plots for offline signature verification

EN Zois, E Zervas, D Tsourounis… - Proceedings of the …, 2020 - openaccess.thecvf.com
In spite of the overwhelming high-tech marvels and applications that rule our digital lives, the
use of the handwritten signature is still recognized worldwide in government, personal and …

Leveraging Expert Models for Training Deep Neural Networks in Scarce Data Domains: Application to Offline Handwritten Signature Verification

D Tsourounis, I Theodorakopoulos, EN Zois… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper introduces a novel approach to leverage the knowledge of existing expert
models for training new Convolutional Neural Networks, on domains where task-specific …

Robust Handwritten Signature Representation with Continual Learning of Synthetic Data over Predefined Real Feature Space

TB Viana, VLF Souza, ALI Oliveira, RMO Cruz… - … on Document Analysis …, 2024 - Springer
Deep learning methods have emerged as state-of-the-art techniques for learning
handwritten signature feature representations. However, successful results in deep learning …

Deep Canonically Correlated Denoising Autoencoders for Signature Verification Purpose

X Zhao, E Chen, P Yuan, L Yuan, Y Zheng - 2024 - researchsquare.com
With the rapid development of modern Internet of Things (IoT) technology, thehandwritten
signature verification system becomes a typical Human-ComputerInteraction (HCI) …

Neural Networks: deep learning strategies for problems with limited data

G Economou, D Tsourounis, A Skodras, E Dermatas… - 2023 - repository-empedu-rd.ekt.gr
Small sample size learning (SSSL) problem arises when the available training data are
limited, making it challenging for machine learning models to capture meaningful patterns …