Scenes detection and recommendation according to web photographs with GPS information

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this age of fast-growing markets for tourism, ever shortening IT development life cycles and ubiquity of digital cameras, the sharing of travel photos on web albums, online communities and personal blogs has become increasingly popular (e.g. through Flickr or Wretch web albums). To mine relevant travel information from the vast troves of photographs on the Internet, the most critical challenge is to analyze and filter the "noises" of travel photographs. We accomplished and implemented this over four stages, and restricted the range of photographs to those taken in Taiwan. Other than displaying highly popular scenic spots, we also tabulated the current popularity of the scenic spots with rankings created with Tourist PageRank. We further attempted to verify the validity of our system with a number of experimental approaches.

Original languageEnglish
Title of host publicationProc. of the IADIS Int. Conf. Intelligent Systems and Agents 2010, Proc. of the IADIS European Conference on Data Mining 2010, Part of the MCCSIS 2010
Pages27-34
Number of pages8
StatePublished - 2010
EventIADIS Int. Conf. Intelligent Systems and Agents 2010,ISA, IADIS European Conference on Data Mining 2010,DM, Part of the MCCSIS 2010 - Freiburg, Germany
Duration: 28 07 201031 07 2010

Publication series

NameProc. of the IADIS Int. Conf. Intelligent Systems and Agents 2010, Proc. of the IADIS European Conference on Data Mining 2010, Part of the MCCSIS 2010

Conference

ConferenceIADIS Int. Conf. Intelligent Systems and Agents 2010,ISA, IADIS European Conference on Data Mining 2010,DM, Part of the MCCSIS 2010
Country/TerritoryGermany
CityFreiburg
Period28/07/1031/07/10

Keywords

  • EXIF
  • Page rank
  • Scenes detection
  • Scenes recommendation

Fingerprint

Dive into the research topics of 'Scenes detection and recommendation according to web photographs with GPS information'. Together they form a unique fingerprint.

Cite this