A preliminary Study on Seasonal features Understanding from Flyer Images Based on Machine Learning

Tomoko Tateyama, Takumi Miyamoto, Ken Orimoto, Shimpei Matsumoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Today, the keyword assignment for advertisements from within digital leaflet images is mainly done manually, and there are problems such as huge amount of task and individual differences in keyword assignment. In this study, we focus on the analysis of flyer images of seasonal events and propose an image categorization method with seasonal information. Many flyer images of seasonal events have designs that represent the season of the event, such as maple leaves in fall and cherry blossoms in spring. We hypothesized that it is possible to classify flyer images by month or season, based on the differences in the designs for each season. For this hypothesis, this study classifies the collected flyer images based on feature detection and machine learning to classify the differences in design by season, and evaluates the classification results.

Original languageEnglish
Title of host publicationProceedings - 2021 10th International Congress on Advanced Applied Informatics, IIAI-AAI 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages668-673
Number of pages6
ISBN (Electronic)9781665424202
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event10th International Congress on Advanced Applied Informatics, IIAI-AAI 2021 - Virtual, Online, Japan
Duration: 11-07-202116-07-2021

Publication series

NameProceedings - 2021 10th International Congress on Advanced Applied Informatics, IIAI-AAI 2021

Conference

Conference10th International Congress on Advanced Applied Informatics, IIAI-AAI 2021
Country/TerritoryJapan
CityVirtual, Online
Period11-07-2116-07-21

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Education

Fingerprint

Dive into the research topics of 'A preliminary Study on Seasonal features Understanding from Flyer Images Based on Machine Learning'. Together they form a unique fingerprint.

Cite this