Presentation 2003/11/14
An Attempt of Indentification of Smilimg, Laughing and Laughter by Computing the Optical-Flows from the Facial Images
Naomi YOSHIKAWA, Masahiro SAKURAI, Michio MIYAKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The final goal of this study is to develop a method to estimate the emotion of a person from his facial images. It was assumed that facial expressions of a smile, laugh and laughter are concerned with the emotion of happiness. We focused on the natural facial expressions of happiness caused by showing an entertainment film to the subjects in this study. From a series of the facial images, the optical-flows were computed around the both eyes and mouth by use of a Kalman filter. We succeeded in identifying such a natural facial expression with correctness of 87.8%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face Recognition / Optical Flow / Kalman filter
Paper # PRMU2003-164,HIP2003-70
Date of Issue

Conference Information
Committee HIP
Conference Date 2003/11/14(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 Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Attempt of Indentification of Smilimg, Laughing and Laughter by Computing the Optical-Flows from the Facial Images
Sub Title (in English)
Keyword(1) Face Recognition
Keyword(2) Optical Flow
Keyword(3) Kalman filter
1st Author's Name Naomi YOSHIKAWA
1st Author's Affiliation Graduate School of Science and Technology. Niigata University()
2nd Author's Name Masahiro SAKURAI
2nd Author's Affiliation Graduate School of Science and Technology. Niigata University
3rd Author's Name Michio MIYAKAWA
3rd Author's Affiliation Faculty of Engineering, Niigata University
Date 2003/11/14
Paper # PRMU2003-164,HIP2003-70
Volume (vol) vol.103
Number (no) 455
Page pp.pp.-
#Pages 6
Date of Issue