CASME II: An Improved Spontaneous Micro-Expression Database and the Baseline Evaluation

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 previous...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PloS one Jg. 9; H. 1; S. e86041
Hauptverfasser: Yan, Wen-Jing, Li, Xiaobai, Wang, Su-Jing, Zhao, Guoying, Liu, Yong-Jin, Chen, Yu-Hsin, Fu, Xiaolan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Public Library of Science 27.01.2014
Public Library of Science (PLoS)
Schlagworte:
Algorithms
Biometry - methods
Brain research
Computer Science
Data bases
Databases, Factual
Datasets
Emotions
Emotions - physiology
Engineering
Evaluation
Face - anatomy & histology
Face - physiology
Facial Expression
Feature extraction
Forensic Sciences - methods
Humans
Information Storage and Retrieval - methods
International conferences
Interrogation
Laboratories
Light
Pattern Recognition, Automated - methods
Police
Questioning
Researchers
Reviews
Social and Behavioral Sciences
Spatial discrimination
Spatial resolution
Support Vector Machine
Temporal resolution
Vision systems
Beijing China
China
ISSN:1932-6203, 1932-6203
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 280×340 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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Conceived and designed the experiments: WJY XF. Performed the experiments: WJY XL. Analyzed the data: WJY SJW. Contributed reagents/materials/analysis tools: WJY. Wrote the paper: WJY XL SJW GZ YHC YJL.
Competing Interests: The authors have declared that no competing interests exist.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0086041