Loading...
Please wait, while we are loading the content...
Similar Documents
CASME II: An Improved Spontaneous Micro-Expression Database and the Baseline Evaluation (2013)
| Content Provider | CiteSeerX |
|---|---|
| Author | Yan, Wen-Jing Li, Xiaobai Wang, Su-Jing Zhao, Guoying Liu, Yong-Jin Chen, Yu-Hsin Fu, Xiaolan |
| Abstract | A robust automatic micro-expression recognition system would have broad applications in national safety, police interrogation, and clinical diagnosis. Developing such a system requires high quality databases with sufficient training samples which are currently not available. We reviewed the previously developed micro-expression databases and built an improved one (CASME II), with higher temporal resolution (200 fps) and spatial resolution (about 2806340 pixels on facial area). We elicited participants ’ facial expressions in a well-controlled laboratory environment and proper illumination (such as removing light flickering). Among nearly 3000 facial movements, 247 micro-expressions were selected for the database with action units (AUs) and emotions labeled. For baseline evaluation, LBP-TOP and SVM were employed respectively for feature extraction and classifier with the leave-one-subject-out cross-validation method. The best performance is 63.41 % for 5-class classification. |
| File Format | |
| Publisher Date | 2013-01-01 |
| Access Restriction | Open |
| Subject Keyword | Casme Ii Baseline Evaluation Improved Spontaneous Micro-expression Database Robust Automatic Micro-expression Recognition System Micro-expression Database Feature Extraction 5-class Classification Police Interrogation Facial Area Leave-one-subject-out Cross-validation Method Well-controlled Laboratory Environment Proper Illumination Temporal Resolution Facial Movement Participant Facial Expression Clinical Diagnosis Action Unit National Safety Sufficient Training Sample Spatial Resolution Broad Application High Quality Database |
| Content Type | Text |
