Identifying Maps on the World Wide Web

Michelson, Matthew; Goel, Aman; Knoblock, Craig A.

doi:10.1007/978-3-540-87473-7_16

Cited by 8 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For that, it is necessary to implement a more efficient but still accurate and robust feature matching method. First experiments with classic CV descriptors (e.g., SURF; Bay et al, 2008) were not promising for the use in topographic maps; instead, water‐filling features (Zhou et al, 1999) have been proposed by Michelson et al (2008) for map classification. Still, a hierarchical matching method, possibly in scale space, is necessary for an efficient coarse‐to‐fine search through a large number of possible locations.…”

Section: Future Workmentioning

confidence: 99%

“…We introduce the use of content‐based image retrieval (CBIR) methods to look for the spatial phenomena of a digitised map in big online geodatabases to predict the map’s most likely location. Content‐based image retrieval is an established method for different applications (Smeulders, Worring, Santini, Gupta, & Jain, 2000) but has so far not found much attention for use with maps (a notable exception being the work by Michelson, Goel, & Knoblock, 2008). However, using CBIR has great potential for processing maps because the availability of both digitised maps and more and more precise volunteered geographic information, most notably on OpenStreetMap (http://www.openstreetmap.org, OSM), has greatly increased (Dorn, Törnros, & Zipf, 2015).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic content‐based georeferencing of historical topographic maps

Luft

Schiewe

2021

Transactions in GIS

View full text Add to dashboard Cite

Old maps are more than a cultural artefact: they are data. Data about the past still hold value for science and decision‐making today. Libraries and archives have come a long way in digitising their inventories of thousands, sometimes millions, of historical maps using high‐resolution scanning. Unfortunately, even with digital images the rich spatial and semantic information is inaccessible for people without a strong background in history and cartography. Only with georeferencing can historical maps be used in GIS and thus processed and compared with modern geospatial data. We introduce content‐based image retrieval to automatically localise and georeference map images from topographic map series. We align the maps by extracting a subset of their symbols and cross‐referencing them with online reference data from OpenStreetMap. We demonstrate our method with the Karte des Deutschen Reiches at 1: 100,000 scale, obtaining 96% correct location predictions and a median georeferencing error of 101 m.

show abstract

Section: Future Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic content‐based georeferencing of historical topographic maps

Luft

Schiewe

2021

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Michelson et al [11] proposed a map identification method using CBIR techniques and edge features. This method searches for similar edges between an input image and a map repository and a non-map repository.…”

Section: Related Workmentioning

confidence: 99%

A deformation analysis method for artificial maps based on geographical accuracy and its applications

Kitayama

Sumiya

2012

Proceedings of the 2nd Joint WICOW/AIRWeb Workshop on Web Quality

View full text Add to dashboard Cite

Artificial maps are widely used for a variety of purposes, including as tourist guides to help people find geographical objects using simple figures. We aim to develop an editing system and a navigation system for artificial maps. Artificial maps made for tourists show suitable objects for traveling users. Therefore, if the artificial map has a navigation system, users can get geographical information such as object positions and routes without performing any operations. However, artificial maps might contain incorrect or superfluous information, such as some objects on the map being intentionally enlarged or omitted. For developing the system, there are two problems: 1. extraction of geographical information from the raster graphics of the artificial map and 2. revision of inaccurate geographical information on the artificial map. We propose a deformation-analyzing method based on geographical accuracy using optical character recognition techniques and comparing gazetteer information. That is, our proposed method detects the tolerance level for deformation according to the purpose of the artificial map. Then, we detect a certain position on the artificial map using deformation analysis. In this paper, we develop a prototype system and we evaluate the accuracy of extracting information from the artificial map and detecting positions.

show abstract

“…A variety of methods to find the maps satisfying a various requirements have been investigated. Michelson et al [10] proposed method for classifying maps from images collected on the Web. In this work, their classifier is based on Water-Filling features, which is edge-based features.…”

Section: Related Workmentioning

confidence: 99%

Analyzing Effective Features based on User Intention for Enhanced Map Search

Matsuo¹,

Kitayama²,

Lee³

et al. 2012

JSW

View full text Add to dashboard Cite

Map would be the most critical information in daily real-world activities. Due to the advance of the Web and digital map processing techniques, we can now easily find various maps of different presentations appropriate to diverse user purposes such as trivial searching for a restaurant or consulting a path during a trip. However, maps served by today’s representative map search engines such as Google Maps cannot satisfy all users whose map-reading ability and search purposes are quite different. Thus, map search engine need to provide maps well represented for specific needs. Nowadays, there are numerous numbers of map contents available on the web, which are appropriately well drawn and shared on various web sites. However, it is not an easy task for users to find out appropriate maps on the Web. In order to support user's map search on the Web, we developed a map search system, which can search for map contents drawn in various viewpoints by interacting with users based on a relevance feedback. In particular, we analyze each map content according to two distinguishing features, geographical features and image features. Significantly, the proposed system can deal with visual map contents by considering how the map contents are represented. In this paper, we analyze effective features based on user intention for map search

show abstract

Identifying Maps on the World Wide Web

Cited by 8 publications

References 14 publications

Automatic content‐based georeferencing of historical topographic maps

Automatic content‐based georeferencing of historical topographic maps

A deformation analysis method for artificial maps based on geographical accuracy and its applications

Analyzing Effective Features based on User Intention for Enhanced Map Search

Contact Info

Product

Resources

About