A facial expression recognition model using hybrid feature selection and support vector machines

Facial expression recognition is a challenging issue in the field of computer vision. Due to the limited feature extraction capability of a single feature descriptor, in this paper, a hybrid feature extraction is utilised. The proposed methodology includes local and global feature extractions that is done by local binary pattern (LBP) and histogram orientation gradient (HOG) respectively. Before applying the feature extraction process, pre-processing and face detection is applied on the face image to extract the useful features. The Viola and Jones algorithm is utilised for face detection and the hybrid Laplacian of Gaussian (HLOG) is used for pre-processing stage. The orthogonal local preserving projection (OLPP)-based dimension reduction algorithm is applied to the extracted features to minimise the computational complexity of the classification algorithm. The SVM classification algorithm is utilised for identifying the facial expression. Here, standard CK+ facial expression dataset is used for evaluating the proposed methodology. The proposed methodology performed well in terms of accuracy compared to the existing PCA + Gabor and PCA + LBP methodology. © 2021 Inderscience Enterprises Ltd.