EMPATH: face, emotion, and gender recognition using holons
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Recognizing Human Facial Expressions From Long Image Sequences Using Optical Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Coding, Analysis, Interpretation, and Recognition of Facial Expressions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic recognition of facial expressions using hidden markov models and estimation of expression intensity
Semisupervised learning of classifiers with application to human-computer interaction
Semisupervised learning of classifiers with application to human-computer interaction
Journal of Cognitive Neuroscience
Facial Expression Recognition Based on Emotion Dimensions on Manifold Learning
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part II
Recognizing facial expressions with PCA and ICA onto dimension of the emotion
SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Facial expression recognition in various internal states using independent component analysis
AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
Hi-index | 0.00 |
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.