Standard
MapReader: a computer vision pipeline for the semantic exploration of maps at scale. / Hosseini, Kasra; Wilson, Daniel C. S.; Beelen, Kaspar et al.
Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022. ed. / Ludovic Moncla; Bruno Martins; Katherine McDonough. New York, NY: Association for Computing Machinery (ACM), 2022. p. 8-19 (Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Hosseini, K, Wilson, DCS, Beelen, K
& McDonough, K 2022,
MapReader: a computer vision pipeline for the semantic exploration of maps at scale. in L Moncla, B Martins & K McDonough (eds),
Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022. Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022, Association for Computing Machinery (ACM), New York, NY, pp. 8-19, SIGSPATIAL '22:, Seattle, United States,
1/11/22.
https://doi.org/10.1145/3557919.3565812APA
Hosseini, K., Wilson, D. C. S., Beelen, K.
, & McDonough, K. (2022).
MapReader: a computer vision pipeline for the semantic exploration of maps at scale. In L. Moncla, B. Martins, & K. McDonough (Eds.),
Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022 (pp. 8-19). (Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022). Association for Computing Machinery (ACM).
https://doi.org/10.1145/3557919.3565812Vancouver
Hosseini K, Wilson DCS, Beelen K
, McDonough K.
MapReader: a computer vision pipeline for the semantic exploration of maps at scale. In Moncla L, Martins B, McDonough K, editors, Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022. New York, NY: Association for Computing Machinery (ACM). 2022. p. 8-19. (Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022). doi: 10.1145/3557919.3565812
Author
Hosseini, Kasra ; Wilson, Daniel C. S. ; Beelen, Kaspar et al. /
MapReader : a computer vision pipeline for the semantic exploration of maps at scale. Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022. editor / Ludovic Moncla ; Bruno Martins ; Katherine McDonough. New York, NY : Association for Computing Machinery (ACM), 2022. pp. 8-19 (Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022).
Bibtex
@inproceedings{335bb40087e74b6789791bf118941009,
title = "MapReader: a computer vision pipeline for the semantic exploration of maps at scale",
abstract = "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 of Britain (≈30.5M patches), foregrounding the challenge of translating visual markers into machine-readable data. We present a case study focusing on rail and buildings. We also show how the outputs from the MapReader pipeline can be linked to other, external datasets. We release ≈62K manually annotated patches used here for training and evaluating the models.",
keywords = "classification, computer vision, deep learning, digital libraries and archives, historical maps, supervised learning",
author = "Kasra Hosseini and Wilson, {Daniel C. S.} and Kaspar Beelen and Katherine McDonough",
year = "2022",
month = nov,
day = "11",
doi = "10.1145/3557919.3565812",
language = "English",
series = "Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022",
publisher = "Association for Computing Machinery (ACM)",
pages = "8--19",
editor = "Ludovic Moncla and Bruno Martins and Katherine McDonough",
booktitle = "Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022",
address = "United States",
note = "SIGSPATIAL '22: : The 30th International Conference on Advances in Geographic Information Systems ; Conference date: 01-11-2022 Through 01-11-2022",
}
RIS
TY - GEN
T1 - MapReader
T2 - SIGSPATIAL '22:
AU - Hosseini, Kasra
AU - Wilson, Daniel C. S.
AU - Beelen, Kaspar
AU - McDonough, Katherine
PY - 2022/11/11
Y1 - 2022/11/11
N2 - 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 of Britain (≈30.5M patches), foregrounding the challenge of translating visual markers into machine-readable data. We present a case study focusing on rail and buildings. We also show how the outputs from the MapReader pipeline can be linked to other, external datasets. We release ≈62K manually annotated patches used here for training and evaluating the models.
AB - 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 of Britain (≈30.5M patches), foregrounding the challenge of translating visual markers into machine-readable data. We present a case study focusing on rail and buildings. We also show how the outputs from the MapReader pipeline can be linked to other, external datasets. We release ≈62K manually annotated patches used here for training and evaluating the models.
KW - classification
KW - computer vision
KW - deep learning
KW - digital libraries and archives
KW - historical maps
KW - supervised learning
U2 - 10.1145/3557919.3565812
DO - 10.1145/3557919.3565812
M3 - Conference contribution/Paper
T3 - Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022
SP - 8
EP - 19
BT - Proceedings of the 6th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2022
A2 - Moncla, Ludovic
A2 - Martins, Bruno
A2 - McDonough, Katherine
PB - Association for Computing Machinery (ACM)
CY - New York, NY
Y2 - 1 November 2022 through 1 November 2022
ER -
