Folkioneer: Efficient Browsing of Community Geotagged Images on a Worldwide Scale

In this paper, we introduce Folkioneer, a novel approach for browsing and exploring community-contributed geotagged images. Initially, images are clustered based on the embedded geographical information by applying an enhanced version of the CURE algorithm, and characteristic geodesic shapes are derived using Delaunay triangulation. Next, images of each geographical cluster are analyzed and grouped according to visual similarity using SURF and restricted homography estimation. At the same time, LDA is used to extract representative topics from the provided tags. Finally, the extracted information is visualized in an intuitive and user-friendly manner with the help of an interactive map.

[1]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[2]  Antony Galton,et al.  Efficient generation of simple polygons for characterizing the shape of a set of points in the plane , 2008, Pattern Recognit..

[3]  Jiri Matas,et al.  Locally Optimized RANSAC , 2003, DAGM-Symposium.

[4]  Yan Zhou,et al.  Minimum Spanning Tree Based Clustering Algorithms , 2006, 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06).

[5]  Sudipto Guha,et al.  CURE: an efficient clustering algorithm for large databases , 1998, SIGMOD '98.

[6]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..