Macro segmentation Computer Vision Project
DataCatalogue
Updated 23 days ago
188
8
Classes (26)
DigitizationArtefactZone
GraphicZone
GraphicZone:Decoration
GraphicZone:FigDesc
GraphicZone:Head
MainZone:Entry
MainZone:Entry#Continued
MainZone:Form
MainZone:Head
MainZone:List
MainZone:Other
MainZone:P
MainZone:P#Continued
MainZone:P@CatalogueDesc
MainZone:Signature
MarginTextZone:ManuscriptAddendum
MarginTextZone:Notes
MarginTextZone:Notes#Continued
NumberingZone
PageTitleZone
PageTitleZone:Index
QuireMarkZone
RunningTitleZone
StampZone
StampZone:Sticker
TableZone
Metrics
Try This Model
Drop an image or
Description
Auction sale catalogues macro segmentation
Document layout analysis dataset for segmenting the macro structure of sale catalogues.
We follow SegmOnto controlled vocabulary (https://segmonto.github.io/) and the COLaF (Inria, ALMAnaCH and Multispeech) schema.
Dataset
Two random folio have been selected from 8 auction sale catalogues collections, kept in the national library of France (Bibliothèque nationale de France, BnF), and the national institute for art history (Institut national d'histoire de l'art, INHA).
- Bienaimé-Feuardent (BnF)
- Bourgey (BnF)
- Dubois (BnF)
- Naville (BnF)
- Rollin (BnF)
- XVIIIe (BnF)
- Desvouges (INHA)
- Lair-Dubreuil (INHA)
Use This Trained Model
Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
LICENSE
CC BY 4.0 If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
macro-segmentation_dataset,
title = { Macro segmentation Dataset },
type = { Open Source Dataset },
author = { DataCatalogue },
howpublished = { \url{ https://universe.roboflow.com/datacatalogue/macro-segmentation } },
url = { https://universe.roboflow.com/datacatalogue/macro-segmentation },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { oct },
note = { visited on 2024-11-21 },
}