Curated datasets, software, and competitions for the Document Image Analysis and Recognition community. https://tc101-demo.github.io/ 2021-09-05T00:00:00Z https://tc101-demo.github.io/competitions/icdar21-mapseg/ 2021-09-05T00:00:00Z 2021-09-05T00:00:00Z

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).

Joseph Chazalon Edwin Carlinet https://tc101-demo.github.io/models/mapseg-baseline-unet/ 2021-06-15T00:00:00Z 2021-06-15T00:00:00Z

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.

Joseph Chazalon https://tc101-demo.github.io/datasets/MapSeg21_1/ 2021-05-27T00:00:00Z 2021-05-27T00:00:00Z

Dataset of the ICDAR 2021 Competition on Historical Map Segmentation (“MapSeg”): segmented map sheets with building blocks, map-content masks, and graticule points.

Joseph Chazalonjoseph.chazalon@lrde.epita.fr Edwin Carlinetedwin.carlinet@lrde.epita.fr https://tc101-demo.github.io/software/icdar21-mapseg-eval/ 2021-05-27T00:00:00Z 2021-05-27T00:00:00Z

Evaluation tools used to score submissions to the ICDAR 2021 MapSeg competition.

Joseph Chazalon https://tc101-demo.github.io/datasets/ICDAR2019-CROHME-TDF_1/ 2020-01-29T00:00:00Z 2020-01-29T00:00:00Z

This package provides training and test data from the competitions CROHME 2011, 2012, 2013, 2014, 2016 and 2019.

Harold Mouchèreharold.mouchere@univ-nantes.fr