| Project/Area Number |
20500194
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
SAKAMOTO Hiroyasu Kyushu University, 芸術工学研究院, 教授 (70112357)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KADOTA Hiroshi 九州大学, 大学院・芸術工学研究院, 教授 (90363390)
FUKUSHIMA Shigehiro 九州大学, 大学院・芸術工学研究院, 教授 (60027927)
WATANUKI Shigeki 九州大学, 大学院・芸術工学研究院, 教授 (00158677)
SAKATA Toshio 九州大学, 大学院・芸術工学研究院, 教授 (20117352)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Project Status |
Completed (Fiscal Year 2010)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2010: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2009: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2008: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
|
|---|
| Keywords | 感性計測評価 / 顔表情画像 / 顔温度画像 / 瞳孔 / 心拍 / 同時解析 / 感情推定 / 感情の次元説 / 刺激映像 / 感情計測 / 心拍周波数 / 同時計測 / 顔表情 / 顔温度 |
|---|
| Research Abstract |
In this research, we first investigated the so-called categorical method and dimensional method for representing human emotions and applied several statistical methods for facial expression images and facial thermal images. It is found that the combination of the dimensional method and the canonical correlation analysis is one of the most effective methods. After developing and constructing our experimental systems and emotion estimating schemes, we conducted experiments for facial data acquisition from test subjects and estimation of their emotions. Similar to the reports of conventional studies, natural and spontaneous facial expressions are quite difficult to be induced and tendencies of fluctuation of facial temperature are different from subject to subject. In spite of these difficulties, we have proposed a method which can estimate a subject's emotion with the same degree of the estimation error as standard deviation of his subjective emotional evaluations.
|
