본문 바로가기
  • Home

Mood Suggestion Framework Using Emotional Relaxation Matching Based on Emotion Meshes

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2018, 23(8), pp.37-43
  • DOI : 10.9708/jksci.2018.23.08.037
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : July 20, 2018
  • Accepted : August 20, 2018
  • Published : August 31, 2018

Jong-Hyun Kim 1

1강남대학교

Accredited

ABSTRACT

In this paper, we propose a framework that automatically suggests emotion using emotion analysis method based on facial expression change. We use Microsoft's Emotion API to calculate and analyze emotion values in facial expressions to recognize emotions that change over time. In this step, we use standard deviations based on peak analysis to measure and classify emotional changes. The difference between the classified emotion and the normal emotion is calculated, and the difference is used to recognize the emotion abnormality. We match user's emotions to relatively relaxed emotions using histograms and emotional meshes. As a result, we provide relaxed emotions to users through images. The proposed framework helps users to recognize emotional changes easily and to train their emotions through emotional relaxation.

Citation status

* References for papers published after 2023 are currently being built.