Facial expression recognition using LBP and LPQ based on Gabor wavelet transform

摘要

In this paper, a novel facial expression recognition method using local binary pattern (LBP) and local phase quantization (LPQ) based on Gabor face image is proposed. To capture the salient visual properties, the Gabor filter is firstly adopted to extract features of the face image among five scales and eight orientations. Then the Gabor image is encoded by the LBP operator and LPQ operator, respectively. Two-stage principal component analysis and linear discriminant analysis (PCA-LDA) approach are used to reduce the dimension of the fused feature combined by the Gabor LBP feature and Gabor LPQ feature. In the experiment, the classification is done by the multi-class SVM classifiers based on the Japanese female facial expression (JAFFE) database. The result shows that the proposed method outperforms many other approaches in this paper in terms of accuracy.