Presentation 2022-03-07
Sightseeing spot detection and automatic generation of explanations using Flickr
Hanami Ookada, Aya Ishino, Toshiyuki Takezawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Using travel photos with latitude and longitude information in Flickr and image recognition technology, we conducted a study to automatically generate image explanations that are useful for tourist information. In this paper, we report the results of the Shimanami Kaido, where many tourist cyclists from Japan and abroad gather. First, using the information obtained from the Google Cloud Vision API as a clue, the photos are automatically classified into five categories: “see”, “eat”, “buy”, “experience”, and “stay”. Next, we detect tourist spots using DBSCAN. Based on the classification information of the images assigned to the tourist spots, a template for the explanation was generated. Furthermore, the explanation of the image was automatically generated by combining the template and the image label for each classification result. From the evaluation experiment, it was found that the explanation of the tourist spot was adequate and fluent, and the explanation was easy to convey to people.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Flickr / image recognition technique / tourism informatics / DBSCAN / sentence generation
Paper # NLC2021-30
Date of Issue 2022-02-28 (NLC)

Conference Information
Committee NLC
Conference Date 2022/3/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Information Processing of Tourism, etc.
Chair Kazutaka Shimada(Kyushu Inst. of Tech.)
Vice Chair Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Takeshi Kobayakawa(NHK)
Secretary Mitsuo Yoshida(Univ. of Tokyo) / Takeshi Kobayakawa(Hiroshima Univ. of Economics)
Assistant Kanjin Takahashi(Sansan) / Ko Mitsuda(NTT)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Sightseeing spot detection and automatic generation of explanations using Flickr
Sub Title (in English)
Keyword(1) Flickr
Keyword(2) image recognition technique
Keyword(3) tourism informatics
Keyword(4) DBSCAN
Keyword(5) sentence generation
1st Author's Name Hanami Ookada
1st Author's Affiliation Hiroshima City University(Hiroshima City Univ.)
2nd Author's Name Aya Ishino
2nd Author's Affiliation Hiroshima University of Economics(HUE)
3rd Author's Name Toshiyuki Takezawa
3rd Author's Affiliation Hiroshima City University(Hiroshima City Univ.)
Date 2022-03-07
Paper # NLC2021-30
Volume (vol) vol.121
Number (no) NLC-415
Page pp.pp.13-18(NLC),
#Pages 6
Date of Issue 2022-02-28 (NLC)