Gabor feature selection for facial expression recognition

This paper presents an effective Gabor features for recognizing the seven basic facial expressions (anger, disgust, fear, happiness, sadness, surprise and neutral) from static images. Entropy criterion selects informative and non-redundant Gabor features. This feature selection reduces the feature dimension without losing much information and also decreases computation and storage requirements. This paper uses improved RBF networks with the proposed effective Gabor features to recognize facial expressions. Experiment results show that our approach can accurately and robustly recognize facial expressions.