ICDAR 2021 Competition on Historical Map Segmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

ICDAR 2021 Competition on Historical Map Segmentation

Pavel Král
  • Function : Author
  • PersonId : 779388
  • IdRef : 13721765X

Abstract

This paper presents the final results of the ICDAR 2021 Competition on Historical Map Segmentation (MapSeg), encouraging research on a series of historical atlases of Paris, France, drawn at 1/5000 scale between 1894 and 1937. The competition featured three tasks, awarded separately. Task 1 consists in detecting building blocks and was won by the L3IRIS team using a DenseNet-121 network trained in a weakly supervised fashion. This task is evaluated on 3 large images containing hundreds of shapes to detect. Task 2 consists in segmenting map content from the larger map sheet, and was won by the UWB team using a U-Net-like FCN combined with a binarization method to increase detection edge accuracy. Task 3 consists in locating intersection points of geo-referencing lines, and was also won by the UWB team who used a dedicated pipeline combining binarization, line detection with Hough transform, candidate filtering, and template matching for intersection refinement. Tasks 2 and 3 are evaluated on 95 map sheets with complex content. Dataset, evaluation tools and results are available under permissive licensing at https://icdar21-mapseg.github.io/.
Fichier principal
Vignette du fichier
chazalon.21.icdar.2.pdf (6.94 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03256193 , version 1 (10-06-2021)

Identifiers

Cite

Joseph Chazalon, Edwin Carlinet, Yizi Chen, Julien Perret, Bertrand Duménieu, et al.. ICDAR 2021 Competition on Historical Map Segmentation. 16th International Conference on Document Analysis and Recognition (ICDAR'21), Sep 2021, Lausanne, Switzerland. pp.693-707, ⟨10.1007/978-3-030-86337-1_46⟩. ⟨hal-03256193⟩
121 View
63 Download

Altmetric

Share

Gmail Facebook X LinkedIn More