Image-based non-contact monitoring of skin texture changed by piloerection for emotion estimation

Mihiro Uchida; Rina Akaho; Keiko Ogawa; Norimichi Tsumura

doi:10.1117/12.2284297

20 February 2018 Image-based non-contact monitoring of skin texture changed by piloerection for emotion estimation

Mihiro Uchida, Rina Akaho, Keiko Ogawa, Norimichi Tsumura

Proceedings Volume 10501, Optical Diagnostics and Sensing XVIII: Toward Point-of-Care Diagnostics; 105010G (2018) https://doi.org/10.1117/12.2284297
Event: SPIE BiOS, 2018, San Francisco, California, United States

Abstract

In this paper, we find the effective feature values of skin textures captured by non-contact camera to monitor piloerection on the skin for emotion estimation. Recently, emotion estimation is required for service robots to interact with human more naturally. There are a lot of researches of estimating emotion and additional methods are required to improve emotion estimation because using only a few methods may not give enough information for emotion estimation. In the previous study, it is necessary to fix a device on the subject’s arm for detecting piloerection, but the contact monitoring can be stress itself and distract the subject from concentrating in the stimuli and evoking strong emotion. So, we focused on the piloerection as the object obtained with non-contact methods. The piloerection is observed as goose bumps on the skin when the subject is emotionally moved, scared and so on. This phenomenon is caused by contraction of arrector pili muscles with the activation of sympathetic nervous system. This piloerection changes skin texture. Skin texture is important in the cosmetic industry to evaluate skin condition. Therefore, we thought that it will be effective to evaluate the condition of skin texture for emotion estimation. The evaluations were performed by extracting the effective feature values from skin textures captured with a high resolution camera. The effective feature values should have high correlation with the degree of piloerection. In this paper, we found that standard deviation of short-line inclination angles in the texture is well correlated with the degree of piloerection.

Citation Download Citation

Mihiro Uchida, Rina Akaho, Keiko Ogawa, and Norimichi Tsumura "Image-based non-contact monitoring of skin texture changed by piloerection for emotion estimation", Proc. SPIE 10501, Optical Diagnostics and Sensing XVIII: Toward Point-of-Care Diagnostics, 105010G (20 February 2018); https://doi.org/10.1117/12.2284297

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