Abstract
A new method for the real-time detection of facial expressions from time-sequential images is proposed. The proposed method does not need the tape marks that are pasted to the face for detecting expressions in real-time in the current implementation for virtual space teleconferencing. In the proposed method, four windows are applied to four areas in the face image: a left and right eye, mouth, and forehead. Each window is divided into blocks that consist of 8 by 8 pixels. Discrete cosine transform (DCT) is applied to each block, and the feature vector of each window is obtained by taking the summations of the DCT energies in the horizontal, vertical, and diagonal directions. To convert the DCT features to virtual tape mark movements, we represent the displacement of a virtual tape mark by a polynomial of the DCT features for the three directions. We apply a genetic algorithm to train facial expression image sequences to find the optimal set of coefficients that minimizes the difference between the real and converted displacements of the virtual tape marks. Experimental results show the effectiveness of the proposed method.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
| Pages | 916-926 |
| Number of pages | 11 |
| Volume | 2727 |
| Edition | 2/- |
| Publication status | Published - 1996 |
| Externally published | Yes |
| Event | Visual Communications and Image Processing'96. Part 2 (of 3) - Orlando, FL, USA Duration: 1996 Mar 17 → 1996 Mar 20 |
Other
| Other | Visual Communications and Image Processing'96. Part 2 (of 3) |
|---|---|
| City | Orlando, FL, USA |
| Period | 96/3/17 → 96/3/20 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Condensed Matter Physics
Cite this
Real-time facial expression detection based on frequency domain transform. / Ebihara, Kazuyuki; Ohya, Jun; Kishino, Fumio.
Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2727 2/-. ed. 1996. p. 916-926.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Real-time facial expression detection based on frequency domain transform
AU - Ebihara, Kazuyuki
AU - Ohya, Jun
AU - Kishino, Fumio
PY - 1996
Y1 - 1996
N2 - A new method for the real-time detection of facial expressions from time-sequential images is proposed. The proposed method does not need the tape marks that are pasted to the face for detecting expressions in real-time in the current implementation for virtual space teleconferencing. In the proposed method, four windows are applied to four areas in the face image: a left and right eye, mouth, and forehead. Each window is divided into blocks that consist of 8 by 8 pixels. Discrete cosine transform (DCT) is applied to each block, and the feature vector of each window is obtained by taking the summations of the DCT energies in the horizontal, vertical, and diagonal directions. To convert the DCT features to virtual tape mark movements, we represent the displacement of a virtual tape mark by a polynomial of the DCT features for the three directions. We apply a genetic algorithm to train facial expression image sequences to find the optimal set of coefficients that minimizes the difference between the real and converted displacements of the virtual tape marks. Experimental results show the effectiveness of the proposed method.
AB - A new method for the real-time detection of facial expressions from time-sequential images is proposed. The proposed method does not need the tape marks that are pasted to the face for detecting expressions in real-time in the current implementation for virtual space teleconferencing. In the proposed method, four windows are applied to four areas in the face image: a left and right eye, mouth, and forehead. Each window is divided into blocks that consist of 8 by 8 pixels. Discrete cosine transform (DCT) is applied to each block, and the feature vector of each window is obtained by taking the summations of the DCT energies in the horizontal, vertical, and diagonal directions. To convert the DCT features to virtual tape mark movements, we represent the displacement of a virtual tape mark by a polynomial of the DCT features for the three directions. We apply a genetic algorithm to train facial expression image sequences to find the optimal set of coefficients that minimizes the difference between the real and converted displacements of the virtual tape marks. Experimental results show the effectiveness of the proposed method.
UR - http://www.scopus.com/inward/record.url?scp=0030392153&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0030392153&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0030392153
SN - 0819421030
SN - 9780819421036
VL - 2727
SP - 916
EP - 926
BT - Proceedings of SPIE - The International Society for Optical Engineering
ER -