|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
GLOBALISE Laypa Region Model - August 2023 |
|
Identification Number: |
hdl:10622/DMAS2T |
|
Distributor: |
IISH Data Collection |
|
Date of Distribution: |
2024-04-11 |
|
Version: |
1 |
|
Bibliographic Citation: |
Klut, Stefan; Koert, Rutger van; Maas, Martijn, 2024, "GLOBALISE Laypa Region Model - August 2023", https://hdl.handle.net/10622/DMAS2T, IISH Data Collection, V1 |
|
Citation |
|
|
Title: |
GLOBALISE Laypa Region Model - August 2023 |
|
Identification Number: |
hdl:10622/DMAS2T |
|
Authoring Entity: |
Klut, Stefan (KNAW Humanities Cluster, Digital Infrastructure) |
|
Koert, Rutger van (KNAW Humanities Cluster, Digital Infrastructure) |
|
|
Maas, Martijn (KNAW Humanities Cluster, Digital Infrastructure) |
|
|
Producer: |
GLOBALISE project |
|
Distributor: |
IISH Data Collection |
|
Access Authority: |
Klut, Stefan |
|
Access Authority: |
IISG Data |
|
Depositor: |
Petram, Lodewijk |
|
Date of Deposit: |
2024-03-05 |
|
Holdings Information: |
https://hdl.handle.net/10622/DMAS2T |
|
Study Scope |
|
|
Keywords: |
Arts and Humanities, Computer and Information Science, handwriting recognition, artificial intelligence model |
|
Abstract: |
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 (<a href="https://hdl.handle.net/10622/QJZKZ2" target="_top">GLOBALISE Ground Truth for Handwritten Text and Layout Recognition</a>) and applied using the <a href="https://github.com/knaw-huc/loghi" target="_top">Loghi Handwritten Text Recognition tools</a> to generate <a href="https://hdl.handle.net/10622/LVXSBW" target="_top">VOC transcriptions v2 - GLOBALISE</a>. The model's hyperparameters are available in the file <code>config.yaml</code>. |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Other Study Description Materials |
|
|
Related Publications |
|
|
Citation |
|
|
Identification Number: |
10622/QJZKZ2 |
|
Bibliographic Citation: |
GLOBALISE Ground Truth for Handwritten Text and Layout Recognition |
|
Citation |
|
|
Identification Number: |
10622/LVXSBW |
|
Bibliographic Citation: |
VOC transcriptions v2 - GLOBALISE |
|
Citation |
|
|
Identification Number: |
10.1145/3604951.3605520 |
|
Bibliographic Citation: |
Stefan Klut, Rutger van Koert, and Ronald Sluijter. 2023. Laypa: A Novel Framework for Applying Segmentation Networks to Historical Documents. In 7th International Workshop on Historical Document Imaging and Processing (HIP ’23), August 25–26, 2023, San Jose, CA, USA. ACM, New York, NY, USA, 6 pages. |
|
Label: |
config.yaml |
|
Notes: |
application/octet-stream |
|
Label: |
model_best_mIoU.pth |
|
Notes: |
application/octet-stream |