The Image Processing and Pattern Recognition group participated in the ANR-funded SoDUCo project (2019–2023), which aimed to study the evolution of the urban spatial structure in relation to the social and professional practices of the population. Focusing on the transformation of Paris between 1789 and 1950, the project combined two rich historical sources:
- A corpus of 16 master maps and the full series of cadastral maps of Paris and its suburbs, documenting the evolution of road networks and the urban fabric.
- Trade directories listing professional activities and/or social status of individuals, geolocated at their addresses.
The project developed methods, models, and tools to automatically extract, verify, and refine information from these sources. It resulted in the creation of an open and structured historical database that enables the analysis and publication of social and urban data at a large scale.
SoDUCo was strongly committed to open science: all publications, data, models, and tools produced during the project were released under open licenses, facilitating reuse across time periods, cities, and research disciplines.
Partners
Related Publications
[1]
Joseph Chazalon • Edwin Carlinet. "Revisiting the Coco Panoptic Metric to Enable Visual and Qualitative Analysis of Historical Map Instance Segmentation". Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR'21). 2021. https://doi.org/10.1007/978-3-030-86337-1_25.
[2]
Yizi Chen • Edwin Carlinet • Joseph Chazalon • Clément Mallet and Bertrand Duménieu • Julien Perret. "Combining Deep Learning and Mathematical Morphology for Historical Map Segmentation". Proceedings of the IAPR International Conference on Discrete Geometry and Mathematical Morphology (DGMM). 2021. https://doi.org/10.1007/978-3-030-76657-3_5.
[3]
Nathalie Abadie • Edwin Carlinet • Joseph Chazalon • Bertrand Duménieu. "A Benchmark of Named Entity Recognition Approaches in Historical Documents". Proceedings of the 15th IAPR International Workshop on Document Analysis System. 5. 2022. https://doi.org/10.1007/978-3-031-06555-2_30.
[4]
Philippe Bernet • Joseph Chazalon • Edwin Carlinet • Alexandre Bourquelot • Élodie Puybareau. "Linear Object Detection in Document Images Using Multiple Object Tracking". Proceedings of the International Conference on Document Analysis and Recognition (ICDAR 2023). 2023. https://doi.org/10.1007/978-3-031-41734-4_28.