Extracting Spatial Information from Historical Maps: Algorithms and Interaction
BoD – Books on Demand, 23 nov. 2018 - 168 pagina's
Historical maps are fascinating documents and a valuable source of information for scientists of various disciplines. Many of these maps are available as scanned bitmap images, but in order to make them searchable in useful ways, a structured representation of the contained information is desirable. This book deals with the extraction of spatial information from historical maps. This cannot be expected to be solved fully automatically (since it involves difficult semantics), but is also too tedious to be done manually at scale. The methodology used in this book combines the strengths of both computers and humans: it describes efficient algorithms to largely automate information extraction tasks and pairs these algorithms with smart user interactions to handle what is not understood by the algorithm. The effectiveness of this approach is shown for various kinds of spatial documents from the 16th to the early 20th century.
Wat mensen zeggen - Een review schrijven
We hebben geen reviews gevonden op de gebruikelijke plaatsen.
Locating Map Elements
Matching Markers and Labels
Extracting Building Footprints
Georeferencing Historical Itineraries
List of Publications
accuracy active learning applied approach Budig building footprints chapter Circulus Franconicus classifier cluster consensus polygon consider contain correct matches corresponding crowdsourcing data set DBSCAN detected digitization Dijk discuss disjoint sets distance documents early prints efficient error measure evaluated example experiments Figure Fragment Assignment gazetteer Geographic Information Retrieval GeoNames georeference georeferencing Glyph Miner glyphs graphical user interface greedy algorithm ground truth groups heuristic hidden Markov model historical itineraries historical maps historical toponym Höhn implementation incorrect information extraction interaction iterations label fragments manually map elements markers and labels modern map modern toponyms OCR system optical character recognition optimal parameter place markers present Raißbüchlin runtime scans Section self-information semantically correct sensitivity analysis shows solution spatial step task template matching text labels threshold user interface user polygons user study variants vertex vertices voting algorithm Würzburg Würzburg University Library