A novel dataset for non-destructive inspection of handwritten documents

E Breci, L Guarnera, S Battiato - arXiv preprint arXiv:2401.04448, 2024 - arxiv.org
Forensic handwriting examination is a branch of Forensic Science that aims to examine
handwritten documents in order to properly define or hypothesize the manuscript's author …

MSDS: A large-Scale Chinese signature and token digit string dataset for handwriting verification

P Zhang, J Jiang, Y Liu, L Jin - Advances in Neural …, 2022 - proceedings.neurips.cc
Although online handwriting verification has made great progress recently, the verification
performances are still far behind the real usage owing to the small scale of the datasets as …

Deep convolutional neural network with KNN regression for automatic image annotation

R Bensaci, B Khaldi, O Aiadi, A Benchabana - Applied Sciences, 2021 - mdpi.com
Automatic image annotation is an active field of research in which a set of annotations are
automatically assigned to images based on their content. In literature, some works opted for …

RSTC: a new residual swin transformer for offline word-level writer identification

P Zhang - IEEE Access, 2022 - ieeexplore.ieee.org
Writer identification has steadily progressed in recent decades owing to its widespread
application. Scenarios with extensive handwriting data such as page-level or sentence-level …

A-VLAD: An end-to-end attention-based neural network for writer identification in historical documents

TT Ngo, HT Nguyen, M Nakagawa - International Conference on …, 2021 - Springer
This paper presents an end-to-end attention-based neural network for identifying writers in
historical documents. The proposed network does not require any preprocessing stages …

Writer identification and writer retrieval based on NetVLAD with Re‐ranking

S Rasoulzadeh, B BabaAli - IET Biometrics, 2022 - Wiley Online Library
The issue of writer identification and writer retrieval, which is considered a challenging
problem in the field of document analysis and recognition is addressed here.. A novel …

Innovative Methods for Non-Destructive Inspection of Handwritten Documents

E Breci, L Guarnera, S Battiato - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Handwritten document analysis is an area of forensic science, with the goal of establishing
authorship of documents through examination of inherent characteristics. Law enforcement …

Towards writer retrieval for historical datasets

M Peer, F Kleber, R Sablatnig - International Conference on Document …, 2023 - Springer
This paper presents an unsupervised approach for writer retrieval based on clustering SIFT
descriptors detected at keypoint locations resulting in pseudo-cluster labels. With those …

Writer characterization from handwriting on papyri using multi-step feature learning

S Nasir, I Siddiqi, M Moetesum - … September 5–10, 2021, Proceedings, Part …, 2021 - Springer
Identification of scribes from historical manuscripts has remained an equally interesting
problem for paleographers as well as the pattern classification researchers. Though …

Offline writer identification approach using moment features and high-order correlation functions

A Litifu, J Xiao, Y Yan, H Jiang - Journal of Visual Communication and …, 2024 - Elsevier
For text-independent writer identification (WI) tasks, this paper proposes a novel method
based on semantic codebooks and two effective feature descriptors. This method requires …