Emotion identification method using RGB information of human face

Shinya Kita, Akira Mita

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Recently, the number of single households is drastically increased due to the growth of the aging society and the diversity of lifestyle. Therefore, the evolution of building spaces is demanded. Biofied Building we propose can help to avoid this situation. It helps interaction between the building and residents' conscious and unconscious information using robots. The unconscious information includes emotion, condition, and behavior. One of the important information is thermal comfort. We assume we can estimate it from human face. There are many researchs about face color analysis, but a few of them are conducted in real situations. In other words, the existing methods were not used with disturbance such as room lumps. In this study, Kinect was used with face-tracking. Room lumps and task lumps were used to verify that our method could be applicable to real situation. In this research, two rooms at 22 and 28 degrees C were prepared. We showed that the transition of thermal comfort by changing temperature can be observed from human face. Thus, distinction between the data of 22 and 28 degrees C condition from face color was proved to be possible.

本文言語English
ホスト出版物のタイトルSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2015
編集者Hoon Sohn, Kon-Well Wang, Jerome P. Lynch
出版社SPIE
ISBN(電子版)9781628415384
DOI
出版ステータスPublished - 2015 1 1
イベントSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2015 - San Diego, United States
継続期間: 2015 3 92015 3 12

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
9435
ISSN(印刷版)0277-786X
ISSN(電子版)1996-756X

Other

OtherSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2015
CountryUnited States
CitySan Diego
Period15/3/915/3/12

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

フィンガープリント 「Emotion identification method using RGB information of human face」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル