We explore a novel application of facial asymmetry: expression classification. Using 2D facial expression images, we show the effectiveness of automatically selected local facial asymmetry for expression recognition. Quantitative evaluations of expression classification using local asymmetry demonstrate statistically significant improvements over expression classification results on the same data set without explicit representation of facial asymmetry. A comparison of discriminative local facial asymmetry features for expression classification versus human identification is given.
Local facial asymmetry for expression classification
2004-01-01
553674 byte
Conference paper
Electronic Resource
English
Local Facial Asymmetry for Expression Classification
| British Library Conference Proceedings | 2004
Facial asymmetry quantification for expression invariant human identification
| British Library Online Contents | 2003
Facial expression recognition based on local binary patterns
| British Library Online Contents | 2007
Robust Facial Expression Recognition using Local Binary Patterns
| British Library Conference Proceedings | 2005