MapReader: A Computer Vision Pipeline for the Semantic Exploration of Maps at Scale

TL;DR

MapReader is an open-source Python library that enables historians to analyze large map collections by transforming maps into searchable, structured data using computer vision techniques, facilitating new insights into historical maps.

Contribution

The paper introduces MapReader, a novel software pipeline that simplifies large-scale map analysis for non-experts and demonstrates its application on extensive 19th-century map collections.

Findings

Enabled analysis of approximately 30.5 million map patches.

Successfully extracted and linked map features to external datasets.

Provided a publicly available annotated dataset for training and evaluation.

Abstract

We present MapReader, a free, open-source software library written in Python for analyzing large map collections (scanned or born-digital). This library transforms the way historians can use maps by turning extensive, homogeneous map sets into searchable primary sources. MapReader allows users with little or no computer vision expertise to i) retrieve maps via web-servers; ii) preprocess and divide them into patches; iii) annotate patches; iv) train, fine-tune, and evaluate deep neural network models; and v) create structured data about map content. We demonstrate how MapReader enables historians to interpret a collection of $\approx$16K nineteenth-century Ordnance Survey map sheets ($\approx$30.5M patches), foregrounding the challenge of translating visual markers into machine-readable data. We present a case study focusing on British rail infrastructure and buildings as depicted on these maps. We also show how the outputs from the MapReader pipeline can be linked to other, external datasets, which we use to evaluate as well as enrich and interpret the results. We release $\approx$62K manually annotated patches used here for training and evaluating the models.