Home // IMMM 2014, The Fourth International Conference on Advances in Information Mining and Management // View article
Authors:
Kohei Tashiro
Atsushi Shimada
Hajime Nagahara
Rin-ichiro Taniguchi
Keywords: user-generated contents, big data analysis, sightseeing spot, sightseeing links, characteristic analysis
Abstract:
In recent years, photo sharing sites such as Flickr, Picasa and others have become popular. These sites are open to public and many photographers upload their photos to share them with family, friends and people in the world. Each photo has several types of metadata including date, time, tags, geo-locations and others, which are automatically produced by a camera or manually provided by the owner. Researchers are interested in such a large-scale image database and use it for image analysis, image annotation, scene understanding and other purposes. Our research focuses on sightseeing images. Analysis of these images shows not only famous sightseeing spots but also links between several sightseeing spots, i.e., popular sightseeing routes. We extract such information through analysis of image metadata. Furthermore, we characterize the sightseeing spots by link type. We developed application software for smartphones in which recommendation information based on the above analyses are displayed. We performed several field tests of real scenes, finding that the recommendation information is useful to travelers.
Pages: 109 to 114
Copyright: Copyright (c) IARIA, 2014
Publication date: July 20, 2014
Published in: conference
ISSN: 2326-9332
ISBN: 978-1-61208-364-3
Location: Paris, France
Dates: from July 20, 2014 to July 24, 2014