Facial Expression Recognition Using a New Image Representation and Multiple Feature Fusion

This paper proposes a novel method for facial expression recognition using a new image representation and multiple feature fusion. First, the new image representation is derived from the normalized hybrid color space, by principal component analysis (PCA) followed by Fisher linear discriminant analysis (FLDA). Second, multi-scale local phase quantization (LPQ) features and patch-based Gabor features are applied to the new image representation and gray-level image, respectively, to extract multiple feature sets. Finally, due to the complementary characteristic between the new image representation and gray-level image, combining the classification results of multiple feature sets at the score level can improve recognition performance further. Experiments on Multi-PIE show that the proposed method achieves state-of-the-art performance for facial expression recognition.