.png){kind=icon}
.png){kind=icon}
Return
EMG-Based Action Unit Recognition: Feature Engineering, Machine Learning, and Real-Time Classification
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-031-96899-0_3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article is an extended version of the work originally presented at the BIODEVICES 2024 conference, which exclusively focuses on utilizing fEMG as the primary method for action unit recognition (AUR). Within the framework of this study, we employ a proprietary dataset of facial electromyography (fEMG) sensor data, which contains synchronized video modality data with fEMG recordings and output labels corresponding to appropriate AUs, to predict a subset of action units. Abundant feature engineering practice and machine learning experiments are conducted to study fEMG-based AUR.
Keywords:
Action units
Electromyography
Facial action coding system
Facial expression
EMG
sEMG
fEMG
Pattern recognition
Machine learning
Journal
B
IF:
0
Papers:
26
Citations:
0