Extracting Forest Cover From Historical Topographic Maps | DORA WSL

Jump to navigation

Saliency and semantic processing: extracting forest cover from historical topographic maps Leyk S, Boesch R & Weibel R ACSAPADORAIEEEVancouverWSL Choose the citation style. Citation Leyk, S., Boesch, R., & Weibel, R. (2006). Saliency and semantic processing: extracting forest cover from historical topographic maps. Pattern Recognition, 39(5), 953-968. https://doi.org/10.1016/j.patcog.2005.10.018 Persistent URL https://www.dora.lib4ri.ch/wsl/islandora/object/wsl:5995

A multi-step recognition process is developed for extracting compound forest cover information from manually produced scanned historical topographic maps of the 19th century. This information is a unique data source for GIS-based land cover change modeling. Based on salient features in the image the steps to be carried out are character recognition, line detection and structural analysis of forest symbols. Semantic expansion implying the meanings of objects is applied for final forest cover extraction. The procedure resulted in high accuracies of 94% indicating a potential for automatic and robust extraction of forest cover from larger areas.

Details Publication Type

Journal Article

Title

Saliency and semantic processing: extracting forest cover from historical topographic maps

Author(s)

Leyk, Stefan (WSL)

Boesch, Ruedi (Landscape Dynamics)

Weibel, Robert

Journal

Pattern Recognition

Volume

39

Issue

5

Start Page

953

End Page

968

Publication Year

2006

Peer Review

Yes

Keywords

historical topographic mapscartographyGIScharacter recognitionline detectionstructural pattern recognitionsemantic processingsaliency

Fulltext:

Published Version Intranet Only

Links:

View at Publisher (DOI) View at Web of Science View at Scopus View at OpenAlex

Citation Counts:

Web of Science: Scopus: Crossref:

Statistics:

Views: 45 Downloads: 2

Feedback:

Suggest a Correction Submit an Accepted Version Add a DOI for Research Data