MapReader: a computer vision pipeline for the semantic exploration of maps at scale

  title={MapReader: a computer vision pipeline for the semantic exploration of maps at scale},
  author={Kasra Hosseini and Daniel C. S. Wilson and Kaspar Beelen and Katherine McDonough},
  journal={Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities},
We present MapReader, a free, open-source software library written in Python for analyzing large map collections. MapReader allows users with little 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 ≈16K nineteenth-century maps… 
2 Citations

Figures and Tables from this paper

Road network evolution in the urban and rural United States since 1900

We examine a key component of human settlements mediating pollution and congestion, as well as economic development: roads and their expansion in cities, towns, and villages. Our analysis of road



Generic Semantic Segmentation of Historical Maps

This work presents a method for computing the figurative diversity of cartographic collections, and discusses the actual opportunities for CNN-based semantic segmentation of historical city maps.

Training Deep Learning Models for Geographic Feature Recognition from Historical Maps

This chapter presents an overview of deep-learning semantic segmentation models and discusses their strengths and weaknesses concerning geographic feature recognition from historical map scans, and presents a comprehensive experiment for extracting railroad features from USGS historical topographic maps as a case study.

The visual digital turn: Using neural networks to study historical images

It is argued that convolutional neural networks allow researchers to explore the visual side of the digital turn and allow archivists and researchers to classify and spot trends in large collections of digitized visual sources in radically new ways.

Maps of a Nation? The Digitized Ordnance Survey for New Historical Research

The ‘patchwork method’ draws on the longstanding desire to adopt an overall or ‘complete’ view of a territory, and highlights certain parallels between the situation faced by today’s users of digitized maps, and a similar inflexion point faced by their predecessors in the nineteenth century as the project to map the nation approached a form of completion.

Billion-scale semi-supervised learning for image classification

This paper proposes a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images to improve the performance for a given target architecture, like ResNet-50 or ResNext.

fastai: A Layered API for Deep Learning

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides

Distant viewing: analyzing large visual corpora

In this article we establish a methodological and theoretical framework for the study of large collections of visual materials. Our framework, distant viewing, is distinguished from other approaches

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

  • Ze LiuYutong Lin B. Guo
  • Computer Science
    2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2021
A hierarchical Transformer whose representation is computed with Shifted windows, which has the flexibility to model at various scales and has linear computational complexity with respect to image size and will prove beneficial for all-MLP architectures.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.