Using Historical Maps in Scientific Studies

Chiang, Yao‐Yi; Duan, Weiwei; Leyk, Stefan; Uhl, Johannes; Knoblock, Craig A.

doi:10.1007/978-3-319-66908-3

Cited by 36 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mentioned aspects often cause unsatisfactory results when applying (semi-)automated text detection and recognition to historical maps. Manual postprocessing becomes necessary as soon as parts of map labels have not been identified or a context to similar words is missing (Chiang et al, 2020;.…”

Section: Current Challenges and State Of Researchmentioning

confidence: 99%

“…Machine learning approaches may enable a universal solution to automatically detect and extract text from a variety of maps. Although their application requires a large amount of input training data it offers the advantage to process data without any manual intervention (Chiang et al, 2020). With Strabo, provide a command line tool for detecting text within maps which is not only based on color differences but also on other characteristics such as the similarity of text sizes or distance measures between individual characters.…”

Section: Current Challenges and State Of Researchmentioning

confidence: 99%

“…As is the case with many applications, Strabo regularly detects only parts of map labels or even omits them entirely. Further manual post-processing is necessary for these results (Chiang et al, 2020). While avoiding an individual editing for each map -whether via preor post-processing -we focus on a universal solution to this issue.…”

Section: Additional Adjustmentsmentioning

confidence: 99%

See 2 more Smart Citations

Automated Extraction of Labels from Large-Scale Historical Maps

Schlegel

2021

AGILE GIScience Ser.

View full text Add to dashboard Cite

Abstract. Historical maps are frequently neither readable, searchable nor analyzable by machines due to lacking databases or ancillary information about their content. Identifying and annotating map labels is seen as a first step towards an automated legibility of those. This article investigates a universal and transferable methodology for the work with large-scale historical maps and their comparability to others while reducing manual intervention to a minimum. We present an end-to-end approach which increases the number of true positive identified labels by combining available text detection, recognition, and similarity measuring tools with own enhancements. The comparison of recognized historical with current street names produces a satisfactory accordance which can be used to assign their point-like representatives within a final rough georeferencing. The demonstrated workflow facilitates a spatial orientation within large-scale historical maps by enabling the establishment of relating databases. Assigning the identified labels to the geometries of related map features may contribute to machine-readable and analyzable historical maps.

show abstract

Section: Current Challenges and State Of Researchmentioning

confidence: 99%

Section: Current Challenges and State Of Researchmentioning

confidence: 99%

Section: Additional Adjustmentsmentioning

confidence: 99%

See 1 more Smart Citation

Automated Extraction of Labels from Large-Scale Historical Maps

Schlegel

2021

AGILE GIScience Ser.

View full text Add to dashboard Cite

show abstract

“…Successful map processing requires georeferencing ( [30]- [35]) and the alignment of georeferenced maps and ancillary spatial data ( [36], [37], see [5], [38] for detailed overviews). Three recent developments are currently changing the field of map processing: 1) An increasing availability of large amounts of scanned, often georeferenced historical maps [39], 2) advances in computer-vision based information extraction using (deep) machine learning [40], and 3) increasing availability of digital geospatial data [41] that can be used as ancillary data to support symbol sample collection.…”

Section: Background a Map Processingmentioning

confidence: 99%

Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Information extraction from historical maps represents a persistent challenge due to inferior graphical quality and the large data volume of digital map archives, which can hold thousands of digitized map sheets. Traditional map processing techniques typically rely on manually collected templates of the symbol of interest, and thus are not suitable for large-scale information extraction. In order to digitally preserve such large amounts of valuable retrospective geographic information, high levels of automation are required. Herein, we propose an automated machine-learning based framework to extract human settlement symbols, such as buildings and urban areas from historical topographic maps in the absence of training data, employing contemporary geospatial data as ancillary data to guide the collection of training samples. These samples are then used to train a convolutional neural network for semantic image segmentation, allowing for the extraction of human settlement patterns in an analysis-ready geospatial vector data format. We test our method on United States Geological Survey historical topographic maps published between 1893 and 1954. The results are promising, indicating high degrees of completeness in the extracted settlement features (i.e., recall of up to 0.96, F-measure of up to 0.79) and will guide the next steps to provide a fully automated operational approach for large-scale geographic feature extraction from a variety of historical map series. Moreover, the proposed framework provides a robust approach for the recognition of objects which are small in size, generalizable to many kinds of visual documents.INDEX TERMS Convolutional neural networks, digital humanities, digital preservation, document analysis, geospatial analysis, geospatial artificial intelligence, human settlement patterns, image analysis, weakly supervised learning.

show abstract

“…This process has involved the visual identification/location of features and their digitization using vector formats that could correspond to points (the fastest of the methods), lines or polygons (which provide extra information such as shape and area but require a higher investment of labour). There has been a recent increase in the development of approaches directed to the automatic vectorization of maps (Chiang et al, 2020;Shbita et al, 2020;. Those cases take advantage of current developments in machine learning (ML) and deep learning (DL) approaches to computer vision (CV), with neural networks (NNs) having a prominent role.…”

Section: Introductionmentioning

confidence: 99%