Paper Info
Title
Facial expression recognition based on two dimensions without neutral expressions
Abstract
We present a new approach for recognizing facial expressions based on two dimensions without detectable cues such as a neutral expression, which has essentially zero motion energy. To remove much of the variability due to lighting, a zero-phase whitening filter was applied. Principal component analysis(PCA) representation excluded the first one principal component as the features for facial expression recognition regardless of neutral expressions was developed. The result of facial expression recognition using a neural network model is compared with two-dimension values of internal states derived from ratings of facial expression pictures related to emotion by experimental subjects. The proposed algorithm demonstrated the ability to overcome the limitation of expression recognition based on a small number of discrete categories of emotional expressions, lighting sensitivity, and dependence on cues such as a neutral expression.
Year
DOI
Venue
2005
10.1007/11558651_21
ICEC
Keywords
Field
DocType
discrete category,principal component analysis,facial expression picture,detectable cue,emotional expression,neutral expression,facial expression,principal component,facial expression recognition,expression recognition,neural network model,two dimensions
Expression (mathematics),Computer science,Emotion recognition,Emotional expression,Artificial intelligence,Artificial neural network,Discrete mathematics,Computer vision,Pattern recognition,Facial expression recognition,Whitening filter,Facial expression,Principal component analysis
Conference
Volume
ISSN
ISBN
3711
0302-9743
3-540-29034-6
Citations 
PageRank 
References 
5
0.65
5
Authors
2
Name
Order
Citations
PageRank
Young-suk Shin1398.39
Young Joon Ahn29111.01