Presentation | 2005/3/17 Quantitative Representation of Face Expression by Motion Capture Hiroaki Yanagisawa, Shinji Sogawa, Akinobu Maejima, Tatsuo Yotsukura, Shigeo Morishima, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we describe a new method of facial expression synthesis from the facial expression data measured by Motion Capture System. Also, as a result of Principal Component Analysis, we can obtain the data that are not correlated with the facial amount of characteristics. Then, we use these data to define how these characteristics make a contribution to facial expressions. The 64 kinds of facial expression data can be obtained by capturing the action unit based on FACS and the combination of those. We put 146 markers on the subject's face and then, use a motion capture system to capture the 3D detailed distance of the marker, while facial expression is changing. After these processes, we apply the obtained distance data to the 3D face model that has been fitting the subject's front picture in order to synthesize the facial expressions. Additionally, we implement Principal Component Analysis in incremental steps to each 3D distance of facial expression and normalize each of these. Through these processes, we propose the parameters of facial expressions that do not correlate with each other. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Motion Capture / Movement Amount Regularization / Principal Component Analysis / Normalization / Eigen-Action Unit |
Paper # | HCS2004-50 |
Date of Issue |
Conference Information | |
Committee | HCS |
---|---|
Conference Date | 2005/3/17(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Human Communication Science (HCS) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Quantitative Representation of Face Expression by Motion Capture |
Sub Title (in English) | |
Keyword(1) | Motion Capture |
Keyword(2) | Movement Amount Regularization |
Keyword(3) | Principal Component Analysis |
Keyword(4) | Normalization |
Keyword(5) | Eigen-Action Unit |
1st Author's Name | Hiroaki Yanagisawa |
1st Author's Affiliation | Science and Engineering, WASEDA University() |
2nd Author's Name | Shinji Sogawa |
2nd Author's Affiliation | Faculty of Engineering, SEIKEI University |
3rd Author's Name | Akinobu Maejima |
3rd Author's Affiliation | Science and Engineering, WASEDA University |
4th Author's Name | Tatsuo Yotsukura |
4th Author's Affiliation | ATR Spoken Language Translation Research Laboratory |
5th Author's Name | Shigeo Morishima |
5th Author's Affiliation | Science and Engineering, WASEDA University |
Date | 2005/3/17 |
Paper # | HCS2004-50 |
Volume (vol) | vol.104 |
Number (no) | 744 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |