Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Master Transcription Regulators

Master Transcription Regulators

Lampbrush Chromosomes

Lampbrush Chromosomes

Transfer RNA Synthesis

Transfer RNA Synthesis

Histone Modification

Histone Modification

Heterochromatin

Heterochromatin

Mechanical Protein Function

Mechanical Protein Function

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Automated analysis of bird head motion in unconstrained settings: a foundational study on semicircular canal evolution in archosaurs.

Journal of the Royal Society, Interface·2025

Same author

Image-Based Shrimp Aquaculture Monitoring.

Sensors (Basel, Switzerland)·2025

Same author

Remote Gait Type Classification System Using Markerless 2D Video.

Diagnostics (Basel, Switzerland)·2021

Same author

A Spatiotemporal Deep Learning Approach for Automatic Pathological Gait Classification.

Sensors (Basel, Switzerland)·2021

Same author

Light Fields for Face Analysis.

Sensors (Basel, Switzerland)·2019

Same author

Automatic Classification of Gait Impairments Using a Markerless 2D Video-Based System.

Sensors (Basel, Switzerland)·2018

Search research articles

Related Experiment Video

Updated: May 26, 2025

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

iForal: Automated Handwritten Text Transcription for Historical Medieval Manuscripts.

Alexandre Matos¹, Pedro Almeida¹, Paulo L Correia²

¹Instituto de Engenharia Eletrónica e Telemática de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal.

Journal of Imaging

|February 25, 2025

Summary

This study introduces an automated system for transcribing historical Portuguese manuscripts, significantly speeding up the process for medieval documents. The developed models accurately recognize layouts, segment text, and perform recognition, aiding palaeographers.

Keywords:

OCR Portuguese documents automatic transcription handwritten text recognition medieval manuscripts text segmentation

More Related Videos

Production of RNA for Transcriptomic Analysis from Mouse Spinal Cord Motor Neuron Cell Bodies by Laser Capture Microdissection

Production of RNA for Transcriptomic Analysis from Mouse Spinal Cord Motor Neuron Cell Bodies by Laser Capture Microdissection

Published on: January 13, 2014

DNA-Tethered RNA Polymerase for Programmable In vitro Transcription and Molecular Computation

DNA-Tethered RNA Polymerase for Programmable In vitro Transcription and Molecular Computation

Published on: December 29, 2021

Related Experiment Videos

Last Updated: May 26, 2025

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

Production of RNA for Transcriptomic Analysis from Mouse Spinal Cord Motor Neuron Cell Bodies by Laser Capture Microdissection

Production of RNA for Transcriptomic Analysis from Mouse Spinal Cord Motor Neuron Cell Bodies by Laser Capture Microdissection

Published on: January 13, 2014

DNA-Tethered RNA Polymerase for Programmable In vitro Transcription and Molecular Computation

DNA-Tethered RNA Polymerase for Programmable In vitro Transcription and Molecular Computation

Published on: December 29, 2021

Area of Science:

Digital Humanities
Computational Linguistics
Historical Document Analysis

Background:

Transcribing historical manuscripts is crucial for cultural heritage accessibility but remains a labor-intensive process.
Automated solutions are needed to accelerate the transcription of medieval documents, particularly Portuguese municipal records.

Purpose of the Study:

To develop and evaluate an automated system for text layout recognition, segmentation, and recognition of historical Portuguese manuscripts.
To contribute an annotated dataset of Portuguese medieval documents for training and benchmarking transcription models.
To facilitate faster and more accurate transcriptions for palaeographers and researchers.

Main Methods:

Development of deep learning models for layout recognition, text segmentation, and text recognition.
Utilizing an annotated dataset of 67 Portuguese royal charter documents from the Middle Ages.
Evaluation of model performance using metrics such as mAP, precision, character error rate (CER), and word error rate (WER).

Main Results:

Layout recognition achieved 0.98 mAP@0.50 and 0.98 precision.
Text segmentation model achieved 0.91 mAP@0.50, detecting 95% of text lines.
Text recognition model yielded 8.1% CER and 25.5% WER on the test set.

Conclusions:

The automated system significantly speeds up the transcription of historical Portuguese manuscripts, enabling faster validation by palaeographers.
The developed models and dataset can serve as a foundation for transcribing other historical handwriting styles, potentially using transfer learning.
The models are compatible with platforms like eSriptorium, benefiting a wide community of experts.