An analysis of the relation between visual concepts and geo-locations using geotagged images on the web

Author

Kawakubo, Hidetoshi ; Yanai, Keiji

Author_Institution

Dept. of Comput. Sci., Univ. of Electro-Commun., Chofu, Japan

fYear

2009

fDate

June 28 2009-July 3 2009

Firstpage

1644

Lastpage

1647

Abstract

Recently, a large number of geotagged images are available on photo sharing Web sites such as Flickr. In this paper, we propose image region entropy and geo-location entropy for analyzing the relation between visual concepts and geographical locations using a large-scale geotagged image database. Image region entropy represents to what extent concepts have visual characteristics, while geo-location entropy represents to what extent concepts are distributed over the world. In the experiment, we analyzed relations between image region entropy and geo-location entropy in terms of 230 nouns and 100 adjectives, and we found that the concepts with low image entropy tend to have high geo-location entropy and vice versa.

Keywords

Web sites; entropy; image representation; probability; very large databases; visual databases; PLSA; geo-location entropy; geographical location; image region entropy representation; large-scale geotagged image database; photo sharing Web site; probabilistic latent semantic analysis; Computer science; Entropy; Image analysis; Image databases; Image texture analysis; Large-scale systems; Performance evaluation; Support vector machine classification; Support vector machines; User-generated content; Flickr; PLSA; bag-offeatures; entropy; geotag;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on

Conference_Location

New York, NY

ISSN

1945-7871

Print_ISBN

978-1-4244-4290-4

Electronic_ISBN

1945-7871

Type

conf

DOI

10.1109/ICME.2009.5202835

Filename

5202835