Multi-pose facial expression recognition using rectangular HOG feature extractor and label-consistent KSVD classifier

Abstract

In this paper, a new approach to the classification of facial expressions from multiple pose images is proposed. In this approach, a rectangular histogram of oriented gradient (R-HOG) algorithm is first designed to extract features of face images. The parameters of the R-HOG algorithm, which is a modification of the original HOG algorithm include cell shape, cell size, block size, and the number of orientation bins. The R-HOG is capable of capturing more discriminative texture features of different facial expressions. In addition, a supervised dictionary learning classifier, the label-consistent K-SVD (LC-KSVD) algorithm, is adopted to recognise the facial expression of the subject. To investigate its effectiveness, the proposed technique was applied to classify emotional states of the face images in the two public available facial expression datasets: KDFE and RafD. The experiment study showed that the new method outperformed in many aspects those methods reported in the literature tested with the same datasets. First, the new method handles pose variations better. Second, it is more robust in cases where the size of a training dataset is small. Finally, it's accuracy performance is more consistent measured by standard deviations.