Historical Map Understanding Using End-to-end Methods
Artificial Intelligence Applications and Innovations (2025)
Abstract
This work deals with processing historical cadastral maps. It is part of a complex system for seamless map creation. The main goal is to detect and recognize so-called nomenclatures, text information composed of several components that specify the position of a map sheet in the coordinate system. This information will then be used to create a large seamless map, allowing for better online presentation. The main contribution of this work is the utilization of a modern end-to-end approach and its comparison with the currently used two-step approach combining text detection and OCR techniques. We chose a visual document understanding model, concretely Donut, for our experiments. The results prove that such models can be successfully trained for our task and outperform the traditional methods.
Authors
BibTex
@inproceedings{lenc2025historical, title={Historical Map Understanding Using End-to-End Methods}, author={Lenc, Ladislav and Mart{\'\i}nek, Ji{\v{r}}{\'\i} and Kr{\'a}l, Pavel}, booktitle={IFIP International Conference on Artificial Intelligence Applications and Innovations}, pages={129--139}, year={2025}, organization={Springer} }
