Abstract
A method that can be used for spotting segments that display facial expression is proposed. The motion of the face is modeled by HMM in such a way that each state corresponds to the conditions of facial muscles, e.g., relaxed, contracting, apex and relaxing. The probability assigned to each state is updated iteratively as the feature vector is obtained from image processing. A spotted segment is placed into a certain category when the probability of that category exceeds a threshold value. Experiments show that the segments for the six basic expressions can be spotted accurately in near real time.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 |
| Publisher | IEEE Computer Society |
| Pages | 442-447 |
| Number of pages | 6 |
| ISBN (Print) | 0818683449, 9780818683442 |
| DOIs | |
| Publication status | Published - 1998 |
| Externally published | Yes |
| Event | 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara Duration: 1998 Apr 14 → 1998 Apr 16 |
Other
| Other | 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 |
|---|---|
| City | Nara |
| Period | 98/4/14 → 98/4/16 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
Spotting segments displaying facial expression from image sequences using HMM. / Otsuka, Takahiro; Ohya, Jun.
Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. p. 442-447 670988.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Spotting segments displaying facial expression from image sequences using HMM
AU - Otsuka, Takahiro
AU - Ohya, Jun
PY - 1998
Y1 - 1998
N2 - A method that can be used for spotting segments that display facial expression is proposed. The motion of the face is modeled by HMM in such a way that each state corresponds to the conditions of facial muscles, e.g., relaxed, contracting, apex and relaxing. The probability assigned to each state is updated iteratively as the feature vector is obtained from image processing. A spotted segment is placed into a certain category when the probability of that category exceeds a threshold value. Experiments show that the segments for the six basic expressions can be spotted accurately in near real time.
AB - A method that can be used for spotting segments that display facial expression is proposed. The motion of the face is modeled by HMM in such a way that each state corresponds to the conditions of facial muscles, e.g., relaxed, contracting, apex and relaxing. The probability assigned to each state is updated iteratively as the feature vector is obtained from image processing. A spotted segment is placed into a certain category when the probability of that category exceeds a threshold value. Experiments show that the segments for the six basic expressions can be spotted accurately in near real time.
UR - http://www.scopus.com/inward/record.url?scp=84905378818&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84905378818&partnerID=8YFLogxK
U2 - 10.1109/AFGR.1998.670988
DO - 10.1109/AFGR.1998.670988
M3 - Conference contribution
AN - SCOPUS:84905378818
SN - 0818683449
SN - 9780818683442
SP - 442
EP - 447
BT - Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
PB - IEEE Computer Society
ER -