GLOBALISE Laypa Region Model - August 2023

GLOBALISE project

This is a Laypa region detection model that was created to detect and identify regions (such as page number, heading, paragraph, and marginalia) on the scans of the GLOBALISE VOC corpus. It was trained on Ground Truth that is also available in this Dataverse (GLOBALISE Ground Truth for Handwritten Text and Layout Recognition) and applied using the Loghi Handwritten Text Recognition tools to generate VOC transcriptions v2 - GLOBALISE. The model's hyperparameters are available in the file config.yaml.

URI
https://hdl.handle.net/10622/DMAS2T (opens in new tab)
Publisher & creator
GLOBALISE project
Part of
https://datasets.iisg.amsterdam/dataverse/globalise (opens in new tab) Browse catalog
License
CC BY 4.0 International (opens in new tab)
Languages
English, Dutch
Keywords
Artificial Intelligence ModelArts and HumanitiesComputer and Information ScienceHandwriting Recognition
Issued
April 15, 2024
Modified
April 15, 2024

Distributions

Download dataset (opens in new tab)
Loading Linked Data summary...

Registration

Registered URL
https://raw.githubusercontent.com/globalise-huygens/knowledge-graph/main/datasets/model_laypa_region_2023.jsonld (opens in new tab) Valid (opens in new tab)
Registered on
April 15, 2024 at 12:39 PM
Last read
6 hours ago
Completeness
95%
Missing properties: dcterms:spatial