Sciweavers

Share
GISCIENCE
2008
Springer

Identifying Maps on the World Wide Web

8 years 4 months ago
Identifying Maps on the World Wide Web
Abstract. This paper presents an automatic approach to mining collections of maps from the Web. Our method harvests images from the Web and then classifies them as maps or non-maps by comparing them to previously classified map and non-map images using methods from Content-Based Image Retrieval (CBIR). Our approach outperforms the accuracy of the previous approach by 20% in F1-measure. Further, our method is more scalable and less costly than previous approaches that rely on more traditional machine learning techniques.
Matthew Michelson, Aman Goel, Craig A. Knoblock
Added 09 Nov 2010
Updated 09 Nov 2010
Type Conference
Year 2008
Where GISCIENCE
Authors Matthew Michelson, Aman Goel, Craig A. Knoblock
Comments (0)
books