Combining image databases for affective image classification

Hye Rin Kim, In Kwon Lee

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

1 Citation (Scopus)

Abstract

Affective image classification has attracted much attention in recent years. However, the production of more exact classifiers depends on the quality of the sample database. In this study, we analyzed various existing databases used for affective image classification and we tried to improve the quality of the learning data by combining existing databases in several different ways. We found that existing image databases cannot cover the overall range of the arousal-valence plane. Thus, to obtain a wider distribution of emotion labels from images, we conducted a crowd-sourcing-based user study with Amazon Mechanical Turk. We aimed to construct several different versions of affective image classifiers by using different combinations of existing databases, instead of using one. We used low-level features in our classification experiments to explore the discriminatory properties of emotion categories. We report the results of intermediate comparisons using different combinations of databases to evaluate the performance of this approach.

Original languageEnglish
Title of host publicationACHI 2015 - 8th International Conference on Advances in Computer-Human Interactions
EditorsLeslie Miller, Alma Leora Culen
PublisherInternational Academy, Research and Industry Association, IARIA
Pages211-212
Number of pages2
ISBN (Electronic)9781612083827
Publication statusPublished - 2015 Jan 1
Event8th International Conference on Advances in Computer-Human Interactions, ACHI 2015 - Lisbon, Portugal
Duration: 2015 Feb 222015 Feb 27

Publication series

NameACHI 2015 - 8th International Conference on Advances in Computer-Human Interactions

Other

Other8th International Conference on Advances in Computer-Human Interactions, ACHI 2015
CountryPortugal
CityLisbon
Period15/2/2215/2/27

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction

Cite this

Kim, H. R., & Lee, I. K. (2015). Combining image databases for affective image classification. In L. Miller, & A. L. Culen (Eds.), ACHI 2015 - 8th International Conference on Advances in Computer-Human Interactions (pp. 211-212). (ACHI 2015 - 8th International Conference on Advances in Computer-Human Interactions). International Academy, Research and Industry Association, IARIA.