Share Email Print

Proceedings Paper

Image-based non-contact monitoring of skin texture changed by piloerection for emotion estimation
Author(s): Mihiro Uchida; Rina Akaho; Keiko Ogawa; Norimichi Tsumura
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 20 February 2018
PDF: 11 pages
Proc. SPIE 10501, Optical Diagnostics and Sensing XVIII: Toward Point-of-Care Diagnostics, 105010G (20 February 2018); doi: 10.1117/12.2284297
Show Author Affiliations
Mihiro Uchida, Chiba Univ. (Japan)
Rina Akaho, Chiba Univ. (Japan)
Keiko Ogawa, Kanazawa Univ. Hospital (Japan)
Norimichi Tsumura, Chiba Univ. (Japan)

Published in SPIE Proceedings Vol. 10501:
Optical Diagnostics and Sensing XVIII: Toward Point-of-Care Diagnostics
Gerard L. Coté, Editor(s)

© SPIE. Terms of Use
Back to Top