Emotion identification method using RGB information of human face

Shinya Kita; Akira Mita

doi:10.1117/12.2084083

27 March 2015 Emotion identification method using RGB information of human face

Shinya Kita, Akira Mita

Proceedings Volume 9435, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2015; 943531 (2015) https://doi.org/10.1117/12.2084083
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2015, San Diego, California, United States

Abstract

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.

Citation Download Citation

Shinya Kita and Akira Mita "Emotion identification method using RGB information of human face", Proc. SPIE 9435, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2015, 943531 (27 March 2015); https://doi.org/10.1117/12.2084083

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available