ICDAR 2021 Competition on Historical Map Segmentation
Dataset of the ICDAR 2021 Competition on Historical Map Segmentation (“MapSeg”): segmented map sheets with building blocks, map-content masks, and graticule points.
ICDAR 2021
Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR 2021)
September 5–10, 2021 · Lausanne, Switzerland
Every dataset, software entry, model, and competition in this catalog that is associated with ICDAR 2021.
Dataset of the ICDAR 2021 Competition on Historical Map Segmentation (“MapSeg”): segmented map sheets with building blocks, map-content masks, and graticule points.
The ICDAR 2021 Competition on Historical Map Segmentation (MapSeg) ran from November 2020 to April 2021. Twelve teams from academia and industry submitted results across the three tasks listed above, evaluated on a held-out test set of historical Paris atlas sheets (1894-1937).
Evaluation tools used to score submissions to the ICDAR 2021 MapSeg competition.
A reference U-Net baseline released alongside the ICDAR 2021 MapSeg competition. The model is trained to perform two of the three competition tasks (building-block detection and map-content segmentation) on 1894-1937 atlas sheets of the City of Paris.
Looking for the proceedings themselves? Try DBLP or Semantic Scholar.