IEICE TRANSACTIONS on Information
Recognition of Facial Expression from Optical Flow
Summary :
We present a method that uses optical flow to estimate facial muscle actions which can then be recognized as facial expressions. Facial expressions are the result of facial muscle actions which are triggered by the nerve impulses generated by emotions. The muscle actions cause the movement and deformation of facial skin and facial features such as eyes, mouth and nose. Since facial skin has the texture of a fine-grained organ, which helps in extracting the optical flow, we can extract muscle actions from external appearance. We are thus able to construct a facial expression recognition system based on optical flow data. We investigate the recogniton method in two ways. First, the optical-flow fields of skin movement is evaluated in muscle winsows, each of which defines one primary direction of muscle contraction to correctly extract muscle movement. Second, a fifteen dimensional feature vector is used to represent the most active points in terms of the flow variance through time and local spatial areas. The expression recognition system uses the feature vector to categorize the image sequences into several classes of facial expression. Preliminary experiments indicate an accuracy of approximately 80% when recognizing four types expressions: happiness, anger, disgust, and surprise.
- Publication
- IEICE TRANSACTIONS on Information Vol.E74-D No.10 pp.3474-3483
- Publication Date
- 1991/10/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Computer Vision and Its Applications)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kenji MASE, "Recognition of Facial Expression from Optical Flow" in IEICE TRANSACTIONS on Information,
vol. E74-D, no. 10, pp. 3474-3483, October 1991, doi: .
Abstract: We present a method that uses optical flow to estimate facial muscle actions which can then be recognized as facial expressions. Facial expressions are the result of facial muscle actions which are triggered by the nerve impulses generated by emotions. The muscle actions cause the movement and deformation of facial skin and facial features such as eyes, mouth and nose. Since facial skin has the texture of a fine-grained organ, which helps in extracting the optical flow, we can extract muscle actions from external appearance. We are thus able to construct a facial expression recognition system based on optical flow data. We investigate the recogniton method in two ways. First, the optical-flow fields of skin movement is evaluated in muscle winsows, each of which defines one primary direction of muscle contraction to correctly extract muscle movement. Second, a fifteen dimensional feature vector is used to represent the most active points in terms of the flow variance through time and local spatial areas. The expression recognition system uses the feature vector to categorize the image sequences into several classes of facial expression. Preliminary experiments indicate an accuracy of approximately 80% when recognizing four types expressions: happiness, anger, disgust, and surprise.
URL: https://global.ieice.org/en_transactions/information/10.1587/e74-d_10_3474/_p
Copy
@ARTICLE{e74-d_10_3474,
author={Kenji MASE, },
journal={IEICE TRANSACTIONS on Information},
title={Recognition of Facial Expression from Optical Flow},
year={1991},
volume={E74-D},
number={10},
pages={3474-3483},
abstract={We present a method that uses optical flow to estimate facial muscle actions which can then be recognized as facial expressions. Facial expressions are the result of facial muscle actions which are triggered by the nerve impulses generated by emotions. The muscle actions cause the movement and deformation of facial skin and facial features such as eyes, mouth and nose. Since facial skin has the texture of a fine-grained organ, which helps in extracting the optical flow, we can extract muscle actions from external appearance. We are thus able to construct a facial expression recognition system based on optical flow data. We investigate the recogniton method in two ways. First, the optical-flow fields of skin movement is evaluated in muscle winsows, each of which defines one primary direction of muscle contraction to correctly extract muscle movement. Second, a fifteen dimensional feature vector is used to represent the most active points in terms of the flow variance through time and local spatial areas. The expression recognition system uses the feature vector to categorize the image sequences into several classes of facial expression. Preliminary experiments indicate an accuracy of approximately 80% when recognizing four types expressions: happiness, anger, disgust, and surprise.},
keywords={},
doi={},
ISSN={},
month={October},}
Copy
TY - JOUR
TI - Recognition of Facial Expression from Optical Flow
T2 - IEICE TRANSACTIONS on Information
SP - 3474
EP - 3483
AU - Kenji MASE
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E74-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 1991
AB - We present a method that uses optical flow to estimate facial muscle actions which can then be recognized as facial expressions. Facial expressions are the result of facial muscle actions which are triggered by the nerve impulses generated by emotions. The muscle actions cause the movement and deformation of facial skin and facial features such as eyes, mouth and nose. Since facial skin has the texture of a fine-grained organ, which helps in extracting the optical flow, we can extract muscle actions from external appearance. We are thus able to construct a facial expression recognition system based on optical flow data. We investigate the recogniton method in two ways. First, the optical-flow fields of skin movement is evaluated in muscle winsows, each of which defines one primary direction of muscle contraction to correctly extract muscle movement. Second, a fifteen dimensional feature vector is used to represent the most active points in terms of the flow variance through time and local spatial areas. The expression recognition system uses the feature vector to categorize the image sequences into several classes of facial expression. Preliminary experiments indicate an accuracy of approximately 80% when recognizing four types expressions: happiness, anger, disgust, and surprise.
ER -
English
